A page interaction method, device, equipment and storage medium

Abstract

The present invention discloses a page interaction method, device, electronic device and storage medium. The method comprises: in response to voice input information associated with a target interface, determining information to be executed according to the voice input information through a voice recognition model; determining a target function module in a candidate function module that matches the information to be executed, the candidate function module comprising function description information and function parameter information; performing corresponding operations on the target task according to the target function module to obtain an execution result of the information to be executed; and returning the execution result to the target interface for visual display. The technical solution of the present application obtains information to be executed through a voice recognition model using the acquired voice input information, determines a target function module for executing the information to be executed and performs a specified operation according to the target function module, and returns the execution result to the target interface for visual display, thereby solving the problem of difficulty in finding page content and realizing rapid operation response of page interaction.

Description

Technical Field

[0001] The present invention relates to the field of page interaction technology, and in particular to a page interaction method, device, equipment and storage medium. Background Art

[0002] In the field of page interaction, traditional pages are restricted by screen size and the amount of page functions displayed is limited. For mobile applications or web pages, the screen space is small. When displaying more functions, paging, page jumps or pop-ups are required. In addition, if the page content is deep, it takes multiple clicks to find a specific function. When the data content is complex and there are many categories, it becomes difficult to find and search.

[0003] In addition, when text needs to be entered during page interaction, it is necessary to use the keyboard to enter it through the text box. If you fill out some lengthy registration forms or complex search keywords on a mobile device, using the keyboard to enter is relatively troublesome and prone to errors. Traditional pages have poor accessibility and lack a complete voice prompt function, making it difficult to understand the page content and perform operations.

[0004] Therefore, the current page interaction has the limitations of limited function display, difficulty in deep content search, inconvenient search when the data is complex, and a single text input method. Summary of the invention

[0005] The present invention provides a page interaction method, device, equipment and storage medium, which solve the problem of difficulty in finding page content and realize rapid operation response of page interaction.

[0006] In a first aspect, an embodiment of the present invention provides a page interaction method, the method comprising:

[0007] In response to the voice input information associated with the target interface, determining the information to be executed according to the voice input information through a voice recognition model; the voice recognition model is generated based on the training of the voice recognition large model; the information to be executed includes the target task to be executed;

[0008] Determine a target function module that matches the information to be executed from the candidate function modules, each of the candidate function modules comprising function description information and function parameter information;

[0009] Execute corresponding operations on the target task according to the target function module to obtain the execution result of the information to be executed;

[0010] The execution result is returned to the target interface for visual display.

[0011] In a second aspect, an embodiment of the present invention further provides a page interaction device, the device comprising:

[0012] A module for determining information to be executed, for responding to voice input information associated with a target interface, and determining information to be executed according to the voice input information through a voice recognition model; the voice recognition model is generated based on training of a large voice recognition model; the information to be executed includes a target task to be executed;

[0013] A target function module determination module is used to determine a target function module that matches the information to be executed among the candidate function modules, each of the candidate function modules comprising function description information and function parameter information;

[0014] An execution result determination module is used to perform corresponding operations on the target task according to the target function module to obtain the execution result of the information to be executed;

[0015] The visualization module is used to return the execution result to the target interface for visual display.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a page interaction method as described in any one of the embodiments of the present invention is implemented.

[0017] In a fourth aspect, an embodiment of the present invention further provides a storage medium storing computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to execute a page interaction method as described in any one of the embodiments of the present invention.

[0018] The technical solution of the embodiment of the present invention obtains the information to be executed through the voice recognition model from the acquired voice input information, determines the target function module for executing the information to be executed and performs the specified operation according to the target function module, and returns the execution result to the target interface for visual display, thereby solving the problem of difficulty in finding page content and realizing rapid operation response of page interaction.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a flow chart of a page interaction method provided by Embodiment 1 of the present invention;

[0022] Figure 2 is a flow chart of a page interaction method provided by Embodiment 1 of the present invention;

[0023] Figure 3 is a structural diagram of a page interaction device provided in Embodiment 2 of the present invention;

[0024] Figure 4 It is a schematic diagram of the structure of an electronic device that implements the page interaction method of an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof 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 necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Embodiment 1

[0028] Figure 1 A flowchart of a page interaction method is provided for the first embodiment of the present invention. This embodiment is applicable to page interaction situations. The method can be executed by a page interaction device. The page interaction device can be implemented in the form of hardware and / or software. The page interaction device can be configured in any electronic device with network communication and computing capabilities. Figure 1 As shown, the method includes:

[0029] S110. In response to the voice input information associated with the target interface, determine the information to be executed according to the voice input information through a voice recognition model; the voice recognition model is generated based on the training of a large voice recognition model; the information to be executed includes the target task to be executed.

[0030] In this embodiment, the target interface refers to an interface for user interaction, and the target interface can be used by the user to query and open information associated with the target interface. Voice input information refers to voice information input to the target interface, which can be understood as voice information input by the user when performing queries or other operations.

[0031] Among them, the speech recognition model represents a model generated based on the training of the speech recognition large model, which is used to convert speech into text content. In this embodiment, the speech recognition model can convert the speech input information into corresponding visual text content. The information to be executed represents the text information associated with the speech input information. The information to be executed includes the target task to be executed. The target task can be a specific matter to be completed by the user or a specific state to be achieved. For example, the information to be executed can be "open the setting menu of the target interface" or "query the rainfall monitoring data of the reservoir in place A".

[0032] This embodiment obtains the user's operation requirements by receiving voice input information associated with the target interface, thereby solving the problem that traditional pages mainly rely on text input from external devices. It is more convenient for some users who are not convenient to type or have slow typing speed to operate the target page, thereby improving input efficiency.

[0033] Furthermore, the speech input information can be recognized and processed by the speech recognition function of the built-in speech recognition model ASR (Automatic Speech Recognition) model, and the speech content can be converted into corresponding text form. For example, if the speech input information is "open the settings menu of the target interface", the speech recognition model can accurately convert it into the corresponding text content, which is convenient for subsequent operations and processing based on the text content.

[0034] S120: Determine a target function module that matches the information to be executed among the candidate function modules, each of the candidate function modules comprising function description information and function parameter information.

[0035] In this embodiment, the candidate function module represents a built-in function associated with the target interface operation. The candidate function module is an independent unit or component that can realize a specific function or complete a specific type of task. It can be a pre-set function module. Each function module includes function description information, function parameter information or function module encoding information. It can be understood that each candidate function module has a clear and relatively independent function set that can meet different task requirements.

[0036] The function description information of each candidate function module indicates the function corresponding to the function module, such as "open news page", "query rainfall data", "display judicial pictures", etc. The function parameter information indicates the parameter information required to operate the function module. For example, the parameter information corresponding to opening the news page may be "date". By entering the target date, the news page of the target date is opened. The function code information may be a code used to uniquely identify the function module. For example, the function code information may be "function module 001", "function module 002" or "function module 003", etc.

[0037] The target functional module represents a functional module for executing the target task of the information to be executed.

[0038] In this embodiment, the target function module matching the information to be executed is determined from the candidate function modules through the text content of the information to be executed. Traditional interaction requires users to click layer by layer to find the function entrance, which is a complicated process. In this embodiment, the target function module to be operated can be directly operated according to the information to be executed, which greatly simplifies the page interaction operation process and improves the efficiency of page interaction operation.

[0039] As an optional but non-limiting implementation, before determining the target function module matching the information to be executed in the candidate function modules, the method includes:

[0040] The information to be executed is standardized by using a natural language processing model to obtain the standardized information to be executed, wherein the natural language processing model is generated based on the training of a large natural language processing model.

[0041] In this embodiment, the natural language processing model is a model generated based on the training of the natural language processing large model, which can be understood as a model that can generate natural language text, understand and process natural language related tasks. By modeling the probability distribution of natural language, the laws and patterns of language are learned so as to predict the next word or generate coherent text based on the given previous context.

[0042] Specifically, in the pre-training stage, the natural language processing model is trained using large-scale unsupervised text data (preset templates) to learn the language knowledge and patterns of the preset templates, wherein the preset templates may be the functional description information of each candidate functional module.

[0043] Common pre-training tasks include language model tasks (such as predicting the next word), masked language model tasks (such as predicting masked words), etc. After pre-training, the natural language processing model can be fine-tuned on a specific natural language processing task. By using a small amount of labeled data to fine-tune the parameters of the natural language processing model, it can better adapt to specific task requirements, such as standardizing the information to be executed, text classification, etc.

[0044] Furthermore, this embodiment can standardize the information to be executed through the trained natural language processing model to obtain the information to be processed with the same text mode as the preset template. For example, if the information to be processed is "help me find a judicial map", after the information to be executed is standardized through the natural language processing model, the text information of "open a judicial map" is obtained, and the information to be processed is described as a specific function to be executed, which is more in line with the text information that can be matched by the candidate function module.

[0045] As an optional but non-limiting implementation, determining a target functional module that matches the information to be executed from among the candidate functional modules includes steps A1-A2:

[0046] Step A1: Determine target function description information that matches the standardized information to be executed.

[0047] Step A2: determine the target function module from the candidate function modules according to the target function description information.

[0048] In this embodiment, the target function description information represents the function description information that matches the information to be executed after the standardization process, and the target function module represents the function module used to execute the target task of the information to be executed.

[0049] It should be noted that each candidate function module includes function description information, wherein the function description information is a description of a specific function, which can indicate the purpose and objective of the function module. For example, the function description information of "open page function" may be "query detailed information according to specific requirements and open the page of current information".

[0050] In actual application, if the standardized information to be executed is "open a judicial diagram", matching is performed according to the functional description information of each candidate functional module. The functional description information with the highest matching degree with the standardized information to be executed is determined as the target functional description information. This step indicates that the candidate functional module corresponding to the target functional description information can complete the specified operation of the target task of the information to be processed.

[0051] Specifically, the function description information having the highest matching degree with the standardized information to be executed may be determined based on a vocabulary overlap method, a semantics method, or a deep learning method.

[0052] This embodiment can determine the degree of match between the information to be executed and the function description information by a method based on deep learning. Specifically, the neural network architecture is first trained. During the training process, matching and non-matching text pairs are used as training data, and the network is trained by minimizing the loss function of matching text pairs and maximizing the loss function of non-matching text pairs. For example, a contrast loss function can be used. When two texts match, the similarity of the network output is close to 1, and close to 0 when they do not match. According to the maximum similarity value, the function description information with the highest matching degree with the standardized information to be executed is determined as the target function description information.

[0053] Furthermore, the candidate function module corresponding to the target function description information may be used as the target function module to execute the target task of the information to be processed.

[0054] As an optional but non-limiting implementation, determining target function description information matching the standardized information to be executed includes steps B1-B2:

[0055] Step B1: Determine keyword information of the information to be executed after standardization.

[0056] Step B2: Determine the target function description information associated with the keyword information.

[0057] In this embodiment, the keyword information refers to words or phrases extracted from the text content of the information to be executed, which have key significance, can accurately summarize the core points, and are helpful for understanding and executing the target task.

[0058] Since the matching of the information to be executed and the function description information focuses more on the keywords of the text, this embodiment determines the target function description information matching the information to be executed through the keyword information of the information to be executed.

[0059] Furthermore, the two texts of the information to be executed and the function description information of the candidate function module can be converted into word bags containing keyword information, respectively. The word bag is a set containing all keywords in the text and their occurrence times, regardless of the order of the keywords. Then, the matching degree between the keyword information of the information to be executed and the function description information is calculated using methods such as cosine similarity, and the function description information with the greatest matching degree with the information to be executed is the target function description information.

[0060] S130: Execute corresponding operations on the target task according to the target function module to obtain execution results of the information to be executed.

[0061] In this embodiment, the execution result indicates the result of executing the target task. It is understandable that if the target task is a consultation question and answer, the execution result is to call the knowledge base information to generate the corresponding answer. If the target task is to operate the target page function, such as changing the font size of the target page, the execution result can be to enlarge or reduce the font of the target page.

[0062] As an optional but non-limiting implementation, performing corresponding operations on the target task according to the target function module to obtain the execution result of the information to be executed includes steps C1-C2:

[0063] Step C1: determining a target parameter value of the function parameter information of the target function module according to the target task.

[0064] Step C2: performing corresponding operations on the target parameter value according to the target function module to obtain the execution result of the information to be executed.

[0065] In this embodiment, the target parameter value represents the parameter value of the function parameter information of the target function module. It should be noted that each candidate function module includes function parameter information, and the function parameter information is used to represent the variables of the function module, such as ID (Identity Document), date or other parameters. For example, for an image color adjustment function module of a target page, the corresponding function parameter information may be color parameters such as brightness, contrast, and saturation. If the target task is to adjust the image color brightness of the target page to 5, the contrast to 10, and the saturation to 15, then the target parameter values ​​5, 10, and 15 required by the function parameter information in the target function module can be extracted according to the target task through the natural language processing model, and the target parameter values ​​are assigned to the function parameter information brightness of 5, contrast of 10, and saturation of 15.

[0066] Furthermore, the target function module performs corresponding operations according to the target parameter values ​​to obtain the execution result of the information to be executed. Taking the target task of adjusting the image color brightness of the target page to 5, the contrast to 10, and the saturation to 15, and the target function module to be the image color adjustment function module as an example, the target parameter values ​​of the function parameter information of the target function module are determined to be 5, 10, and 15 respectively according to the target task. The image color adjustment function module adjusts the image color parameters of the current page according to the target parameter values, so that the image color of the current page achieves the effect of brightness of 5, contrast of 10, and saturation of 15.

[0067] As an optional but non-limiting implementation, the target task is operated according to the target function module to obtain the execution result of the information to be executed, and the steps D1-D2 are also included:

[0068] Step D1: perform corresponding operations on the target task according to the target function module to obtain an execution result list of information to be executed.

[0069] Step D2: In response to the trigger information associated with the target interface, determine the execution result of the information to be executed from the execution result list.

[0070] In this embodiment, the execution result list is a series of execution results obtained by executing corresponding operations on the target task according to the target function module. The trigger information represents the external input information accepted by the target interface, which can be the user's trigger button operation, voice input or text input and other information.

[0071] It should be noted that the execution result list contains at least one execution result. For example, in a data query task, the execution result items may be data records that meet the query conditions, and each record contains specific information such as name, age, occupation, etc. If the target task of the information to be executed does not contain the specific parameter value of the function parameter information, it is necessary to determine the execution result of the information to be executed from the execution result list through external trigger information.

[0072] S140: Return the execution result to the target interface for visual display.

[0073] In this embodiment, the target page responds to external voice input information and displays the corresponding execution result.

[0074] As an optional but non-limiting implementation, returning the execution result to the target interface for visual display includes:

[0075] The execution result is converted into voice output information for broadcast using a text conversion model, wherein the text conversion model is trained and generated based on a large text-to-speech model.

[0076] In this embodiment, the text conversion model refers to a model generated based on the training of the text-to-speech model, which can convert text information into natural and smooth speech output. Corresponding speech output information can be preset for different execution results, for example, "opening completed", "modification successful", "query failed", etc. This embodiment does not specifically limit the content of the announcements in different scenarios.

[0077] This embodiment solves the limitation of the traditional page interaction function being relatively fixed and the information output being in a single form. When facing consultation questions and answers, this embodiment can not only display the answers on the page, but also convert them into voice output according to special needs. The flexible information output method can better meet the needs of different users in different scenarios.

[0078] See also Figure 2The figure shows a flow chart of the page interaction method, in which the user interacts on the target page through the chat box on the display screen. The target page is configured with corresponding candidate function modules. Each candidate function module contains corresponding function codes, function parameter information and function description information (parameter fields). The function codes are used to describe the IDs of each candidate function module, the function parameter information is used to describe the parameters required for each candidate function module, and the function description information is used to describe the functions or operations implemented by each candidate function module.

[0079] Furthermore, the large model management platform can add, delete, modify and check each candidate functional module to facilitate the upgrade and maintenance of the target interface interaction process. Furthermore, the large model management platform can encapsulate each candidate functional module and generate a corresponding functional module set to facilitate the response to the voice input information or text input information of the target interface.

[0080] The speech recognition model can be used to convert the speech input information associated with the target interface into information to be executed in text form. Taking the information to be executed as "open a judicial picture" as an example, the information to be executed is standardized through the natural language processing model. According to the target task of the information to be executed, the target function module with the function of "opening the picture" is determined from the packaged function module set, and the code of the target function module is called to return "a judicial picture". If the target task contains the required target parameter value of the function parameter information of the target function module, the target parameter value is unique, and the judicial picture corresponding to the target parameter value can be returned to the target page for visual display through the target function module. If the target task does not contain the required target parameter value of the function parameter information of the target function module, the target function module returns a judicial picture list containing at least one judicial picture. The user determines the target judicial picture based on the judicial picture list and displays it visually on the target page.

[0081] The technical solution of the embodiment of the present invention obtains the information to be executed by using the acquired voice input information through a voice recognition model, determines the target function module for executing the information to be executed and performs the specified operation according to the target function module, and returns the execution result to the target interface for visual display, thereby solving the problem of difficulty in finding page content and realizing rapid operation response of page interaction.

[0082] Embodiment 2

[0083] Figure 3 This is a schematic diagram of the structure of a page interaction device provided in the second embodiment of the present invention. This embodiment is applicable to page interaction situations. The page interaction device can be implemented in the form of hardware and / or software. The page interaction device can be configured in any electronic device with network communication and computing capabilities. Figure 3 As shown, the device comprises:

[0084] The to-be-executed information determination module 310 is used to determine the to-be-executed information according to the voice input information associated with the target interface through a voice recognition model; the voice recognition model is generated based on the training of the voice recognition large model; the to-be-executed information includes the target task to be executed;

[0085] A target function module determination module 320 is used to determine a target function module that matches the information to be executed from among the candidate function modules, each of which includes function description information and function parameter information;

[0086] An execution result determination module 330 is used to perform corresponding operations on the target task according to the target function module to obtain the execution result of the information to be executed;

[0087] The visualization module 340 is used to return the execution result to the target interface for visualization.

[0088] Optionally, before determining the target function module matching the information to be executed in the candidate function modules, the method includes:

[0089] The information to be executed is standardized by using a natural language processing model to obtain the standardized information to be executed, wherein the natural language processing model is generated based on the training of a large natural language processing model.

[0090] Optionally, determining a target functional module that matches the information to be executed in the candidate functional modules includes:

[0091] Determine target function description information that matches the standardized information to be executed;

[0092] The target function module is determined from the candidate function modules according to the target function description information.

[0093] Optionally, determining target function description information that matches the standardized information to be executed includes:

[0094] Determine keyword information of the information to be executed after the standardized processing;

[0095] Determine target function description information associated with the keyword information.

[0096] Optionally, performing corresponding operations on the target task according to the target function module to obtain execution results of the information to be executed includes:

[0097] Determine the target parameter value of the function parameter information of the target function module according to the target task;

[0098] According to the target function module, a corresponding operation is performed on the target parameter value to obtain an execution result of the information to be executed.

[0099] Optionally, performing corresponding operations on the target task according to the target function module to obtain the execution result of the information to be executed also includes:

[0100] Execute corresponding operations on the target task according to the target function module to obtain an execution result list of the information to be executed;

[0101] In response to the trigger information associated with the target interface, the execution result of the information to be executed is determined from the execution result list.

[0102] Optionally, returning the execution result to the target interface for visual display includes:

[0103] The execution result is converted into voice output information for broadcast using a text conversion model, wherein the text conversion model is trained and generated based on a large text-to-speech model.

[0104] The technical solution of the embodiment of the present invention obtains the information to be executed by using the acquired voice input information through a voice recognition model, determines the target function module for executing the information to be executed and performs the specified operation according to the target function module, and returns the execution result to the target interface for visual display, thereby solving the problem of difficulty in finding page content and realizing rapid operation response of page interaction.

[0105] The page interaction device provided in the embodiment of the present invention can execute the page interaction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0106] Embodiment 3

[0107] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention 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 can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0108] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0109] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0110] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a page interaction method.

[0111] In some embodiments, the page interaction method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the page interaction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the page interaction method in any other appropriate manner (e.g., by means of firmware).

[0112] Various implementations 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 chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0114] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0115] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0116] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0117] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0118] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0119] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A page interaction method, characterized in that: include: In response to the voice input information associated with the target interface, determining the information to be executed according to the voice input information through the voice recognition model; The speech recognition model is generated based on speech recognition large model training; the information to be executed includes the target task to be executed; Determine a target function module that matches the information to be executed from the candidate function modules, each of the candidate function modules comprising function description information and function parameter information; Execute corresponding operations on the target task according to the target function module to obtain the execution result of the information to be executed; The execution result is returned to the target interface for visual display.

2. The method according to claim 1, characterized in that Before determining the target function module matching the information to be executed in the candidate function modules, the following steps are included: The information to be executed is standardized by using a natural language processing model to obtain the standardized information to be executed, wherein the natural language processing model is generated based on the training of a large natural language processing model.

3. The method according to claim 2, characterized in that Determine the target function module that matches the information to be executed among the candidate function modules, including: Determine target function description information that matches the standardized information to be executed; The target function module is determined from the candidate function modules according to the target function description information.

4. The method according to claim 3, characterized in that Determine the target function description information that matches the standardized information to be executed, including: Determine keyword information of the information to be executed after the standardized processing; Determine target function description information associated with the keyword information.

5. The method according to claim 1, characterized in that Execute corresponding operations on the target task according to the target function module to obtain the execution result of the information to be executed, including: Determine the target parameter value of the function parameter information of the target function module according to the target task; According to the target function module, a corresponding operation is performed on the target parameter value to obtain an execution result of the information to be executed.

6. The method according to claim 1, characterized in that Executing corresponding operations on the target task according to the target function module to obtain the execution result of the information to be executed also includes: Execute corresponding operations on the target task according to the target function module to obtain an execution result list of the information to be executed; In response to the trigger information associated with the target interface, the execution result of the information to be executed is determined from the execution result list.

7. The method according to claim 1, characterized in that Returning the execution result to the target interface for visual display includes: The execution result is converted into voice output information for broadcast using a text conversion model, wherein the text conversion model is trained and generated based on a large text-to-speech model.

8. A page interaction device, characterized in that: include: The to-be-executed information determination module is used to determine the to-be-executed information according to the voice input information by using a voice recognition model in response to the voice input information associated with the target interface; The speech recognition model is generated based on speech recognition large model training; the information to be executed includes the target task to be executed; A target function module determination module is used to determine a target function module that matches the information to be executed among the candidate function modules, each of the candidate function modules comprising function description information and function parameter information; An execution result determination module is used to perform corresponding operations on the target task according to the target function module to obtain the execution result of the information to be executed; The visualization module is used to return the execution result to the target interface for visual display.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the page interaction method as described in any one of claims 1-7 is implemented.

10. A storage medium storing computer executable instructions, characterized in that: The computer executable instructions are used to execute the page interaction method as described in any one of claims 1-7 when executed by a computer processor.

Images