Page interaction method and device, equipment and medium
By using a voice interaction system in the web software of an oil and gas station or oil depot, combined with hierarchical paths and preset instructions, users can quickly jump to pages through voice commands, solving the problem of relying on manual operations and low efficiency in the existing technology. Improves interaction efficiency and user experience.
Patent Information
- Application Number
- CN202411152691.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-12-06
AI Technical Summary
The existing page interaction method relies on manual operations in the web software of oil and gas stations or oil depots, and cannot quickly jump to the pages that users are interested in, and there are problems such as low information management efficiency and difficulty in finding target pages.
By obtaining the hierarchical path and preset instructions of the web page, combining voice commands to match similarity, determine the target command and execute it, the activation of the voice interaction system and page jump are realized, and seamless jump between pages at any level is supported.
It enables users to easily jump to pages without keyboard or mouse through voice commands, save bandwidth and computing resources, and improve interaction efficiency and user experience.
Smart Images

Figure CN119091882A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of Internet technology, and in particular to a page interaction method, device, equipment and medium. Background Art
[0002] In the process of web-based software interaction at oil and gas stations or oil depots, the mouse and keyboard interaction method is often used, that is, users interact with web pages by clicking the mouse, inputting text on the keyboard, or operating interface elements. This method is a traditional and widely used interaction method. In addition to requiring users to have certain keyboard and mouse operation skills, this method also has the following disadvantages: relying on manual information management; unable to quickly jump to the page that the user is interested in; and having the trouble of finding the target page in the whole system.
[0003] Based on this, a new way of page interaction is urgently needed. Summary of the invention
[0004] The present application provides a page interaction method, device, equipment and medium to solve the above-mentioned problems existing in the existing page interaction methods.
[0005] In a first aspect of an embodiment of the present application, a page interaction method is provided, which is applied to a page interaction system. The method includes:
[0006] Acquire a second path for operating each page in the webpage, where the second path is determined by the first path, the second path is a global path for operating each page, and the first path is a hierarchical path for operating each page;
[0007] Associating the second path corresponding to each page with a preset instruction of each page, wherein the preset instruction is used to operate a web page in a scenario of an oil and gas station or an oil depot;
[0008] Acquire a voice command, and determine whether the page interaction system is in an activated state based on the voice command;
[0009] When the page interaction system is in an activated state and the voice instruction contains a user intended word, similarity matching is performed between the user intended word and all preset instructions;
[0010] When the similarity obtained by matching is greater than or equal to a preset threshold, determining a target instruction, wherein the target instruction is a preset instruction corresponding to the maximum similarity;
[0011] The voice instruction is executed based on the second path corresponding to the preset instruction corresponding to the maximum similarity.
[0012] In an optional embodiment of the present application, hierarchical structure information of pages at all levels in a webpage and a first path for operating each page are obtained, and the webpage is a webpage in a scenario of an oil and gas station or an oil depot;
[0013] Based on the hierarchical structure information, horizontal structure information is generated, and based on the horizontal structure information, the first path is changed to the second path.
[0014] In an optional embodiment of the present application, obtaining a voice instruction, and determining whether the page interaction system is in an activated state based on the voice instruction includes:
[0015] Determining whether the voice command contains an activation word;
[0016] In the case where the voice instruction includes the activation word, determining the volume of the voice instruction;
[0017] When the volume of the voice command is greater than or equal to a preset volume, the state of the page interaction system is switched to an activated state.
[0018] In an optional embodiment of the present application, after the page interaction system is in an activated state, the process includes:
[0019] When the page interaction system is in an activated state, the voice command is sent to an edge voice recognition model, and text recognition is performed on the voice command to obtain text information corresponding to the voice command;
[0020] A user intention word in the text information is obtained, where the user intention word is used to characterize at least one of a user's operation behavior and an operation object.
[0021] In an optional embodiment of the present application, after executing the voice instruction, the method further includes:
[0022] Generate first result information, where the first result information is used to indicate that the target instruction has been executed;
[0023] In response to the first result information, generating and playing first voice feedback information based on the target instruction, and maintaining an activation state;
[0024] Re-identify a new voice command, and switch from an active state to an inactive state if the new voice command is an invalid voice command and lasts for a preset time, wherein the invalid voice command includes: the volume of the new voice command is less than a preset volume, or the new voice command cannot be recognized.
[0025] In an optional embodiment of the present application, the voice command is used to cause the webpage to jump to the first page. After executing the voice command, the method further includes:
[0026] When the page interaction system is in an activated state, obtaining a new voice command, wherein the new voice command is used to make the webpage jump to a second page, wherein the second page and the first page are pages of different levels in the hierarchical structure information;
[0027] The new voice command is executed to cause the web page to jump from the first page to the second page.
[0028] In an optional embodiment of the present application, when the page interaction system is in an activated state, the method further includes:
[0029] If the voice command does not include the user intended word, generating second result information, where the second result information is used to indicate that the corresponding voice command cannot be executed;
[0030] In response to the second result information, the corresponding second voice feedback information is played and the activation state is maintained.
[0031] In an optional embodiment of the present application, when the page interaction system maintains an activated state, the method further includes:
[0032] Re-recognizing a new voice instruction, wherein the new voice instruction includes an operation intention word;
[0033] In the case where the operation intention word only represents an operation behavior, determining whether the operation intention word is an exit intention word;
[0034] In the case where the operation intention word includes an exit intention, generating third result information, wherein the third result information is used to indicate that the exit intention has been executed;
[0035] In response to the third result information, third voice feedback information is played based on the exit intention.
[0036] In an optional embodiment of the present application, the method further includes:
[0037] Get the third path corresponding to each pop-up window contained in all pages;
[0038] Set the command to close each pop-up window as the default close command;
[0039] Correspondingly associating the preset closing instruction corresponding to each pop-up window with the third path;
[0040] When the page interaction system is in an activated state and the user intention word is only characterized by closing the pop-up window, the preset closing instruction is executed based on the third path.
[0041] In a second aspect of an embodiment of the present application, a page interaction device is provided, the device comprising:
[0042] A path acquisition module, used to acquire a second path for operating each page in a webpage, wherein the second path is determined by the first path, the second path is a global path for operating each page, and the first path is a hierarchical path for operating each page;
[0043] An association module, used to associate the second path corresponding to each page with a preset instruction of each page, wherein the preset instruction is used to operate a web page in an oil and gas station or oil depot scenario;
[0044] A voice instruction acquisition module, used to acquire voice instructions and determine whether the page interaction system is in an activated state based on the voice instructions;
[0045] A matching module, configured to perform similarity matching between the user intended word and all preset instructions when the page interaction system is in an activated state and the voice instruction contains the user intended word;
[0046] A target instruction determination module, used to determine a target instruction when the similarity obtained by matching is greater than or equal to a preset threshold, wherein the target instruction is a preset instruction corresponding to the maximum similarity;
[0047] The target execution module is used to execute the voice instruction based on the second path corresponding to the preset instruction corresponding to the maximum similarity.
[0048] In a third aspect of an embodiment of the present application, an electronic device is proposed, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the page interaction method described in any one of the first aspects above.
[0049] In a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, the page interaction method described in any one of the first aspects above is implemented.
[0050] The present application includes the following advantages: The present application proposes a page interaction method, device, equipment and medium, by obtaining the second path for operating each page in the web page, the second path is determined by the first path, the second path is the global path for operating each page, and the first path is the hierarchical path for operating each page; the second path corresponding to each page is associated with the preset instruction of each page, and the preset instruction is used to operate the web page in the oil and gas station or oil depot scene; obtain voice instructions, and judge whether the page interaction system is in an activated state based on the voice instructions; when the page interaction system is in an activated state and the voice instruction contains a user intention word, the user intention word is matched with all preset instructions for similarity; when the similarity obtained by matching is greater than or equal to a preset threshold, the target instruction is determined, and the target instruction is the preset instruction corresponding to the maximum similarity; based on the second path corresponding to the preset instruction corresponding to the maximum similarity, the voice instruction is executed. The above method can realize the jump between pages of any level according to the preset instructions by seamlessly integrating the voice interaction function with the existing web pages, so that users can use voice interaction very conveniently while greatly saving bandwidth and computing resources. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0052] Figure 1 It is a schematic diagram of the steps of a page interaction method proposed in an embodiment of the present application;
[0053] Figure 2 This is one of the flow diagrams of a page interaction method proposed in an embodiment of the present application;
[0054] Figure 3 This is the second flow chart of a page interaction method proposed in an embodiment of the present application;
[0055] Figure 4 It is a functional structure diagram of a page interaction device proposed in an embodiment of the present application;
[0056] Figure 5 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0057] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0058] In the process of web-based software interaction at oil and gas stations or oil depots, the mouse and keyboard interaction method is often used, that is, users interact with web pages by clicking the mouse, inputting text on the keyboard, or operating interface elements. This method is a traditional and widely used interaction method. In addition to requiring users to have certain keyboard and mouse operation skills, this method also has the following disadvantages: relying on manual information management; unable to quickly jump to the page that the user is interested in; and having the trouble of finding the target page in the whole system.
[0059] Based on this, the present application proposes a page interaction method: users can directly use voice commands to perform operations or obtain information without interacting with the page through keyboard input or mouse clicks.
[0060] In a first aspect of an embodiment of the present application, a page interaction method is proposed, and the page interaction method is applied to a page interaction system, referring to Figure 1 , Figure 1 : is a schematic diagram of a step flow of a page interaction method proposed in an embodiment of the present application, the method comprising the following steps:
[0061] Step 101: obtaining a second path for operating each page in a webpage, wherein the second path is determined by the first path, the second path is a global path for operating each page, and the first path is a hierarchical path for operating each page;
[0062] Step 102: Correspondingly associating the second path corresponding to each page with a preset instruction of each page, wherein the preset instruction is used to operate a web page in a scenario of an oil and gas station or an oil depot;
[0063] Step 103: Acquire a voice command, and determine whether the page interaction system is in an activated state based on the voice command;
[0064] Step 104: When the page interaction system is in an activated state and the voice instruction contains a user intended word, similarity matching is performed between the user intended word and all preset instructions;
[0065] Step 105: When the similarity obtained by matching is greater than or equal to a preset threshold, determining a target instruction, wherein the target instruction is a preset instruction corresponding to the maximum similarity;
[0066] Step 106: Execute the voice instruction based on the second path corresponding to the preset instruction corresponding to the maximum similarity.
[0067] In order to clearly illustrate a page interaction method proposed in an embodiment of the present application, the following Figure 2 and Figure 3 For detailed explanation, Figure 2 This is one of the flow diagrams of a page interaction method proposed in an embodiment of the present application. Figure 3 This is the second flow chart of a page interaction method proposed in an embodiment of the present application.
[0068] When implementing step 101, in order to realize that the above-mentioned page interaction system can seamlessly integrate the voice interaction function with the pages in the existing web pages or applications, and the user can obtain the web page content across levels, the present application first obtains the second path for each page in the operation web page, wherein the second path is the global path for operating each page, and the above-mentioned second path is determined by the first path, and the first path is the hierarchical path for operating each page.
[0069] In an optional embodiment of the present application, obtaining the second path for operating each page in a web page specifically includes the following process: first, obtaining the hierarchical structure information of each level of pages in the web page, and the first path for operating each page, and the web page is a web page in an oil and gas station or oil depot scenario. Optionally, if it is an interaction with an application page, the hierarchical structure information of each page of the application is obtained accordingly, and the path for operating each page is obtained. The operations of the two are substantially different, and the following is explained based on the page interaction in the web page.
[0070] In the embodiment of the present application, the hierarchical relationship of each page refers to the relationship between the page and its subpages. For example, the function page corresponding to the homepage of the webpage is the first page, and its corresponding hierarchical relationship is the first level. The first page contains pages A, B, and C, and its corresponding hierarchical relationship is the second level. Page A contains pages a and b, and page B contains pages c and d, and its corresponding hierarchical relationship is the third level. The first path is exemplified by the pages listed above. The first path corresponding to operating page a is the path of operating page A after operating the first page. This path is the first path for operating page a.
[0071] Then, after obtaining the hierarchical structure information of each page, based on the hierarchical structure information, the horizontal structure information is generated, so that the user can directly obtain the webpage content across levels and jump to the corresponding page, making the user operation more convenient. At the same time, based on the horizontal structure information, the first path for operating each page is changed to the second path, and the above-mentioned second path is the global path for operating each page. Changing the hierarchical structure information to the horizontal structure information means changing the levels of all pages to the same level. For example, the hierarchical relationship corresponding to the second-level page A, page B and page C, or the third-level page a, page b, page c and page d are all changed to the first level, then the page structure of each page after the change is horizontal. The path for operating each page also changes accordingly. For example, if it is on the first page at this time, the second path corresponding to the operation of page a is to directly open page a. If it is on page A at this time, the second path corresponding to the operation of page c is to directly open page c.
[0072] When step 102 is specifically implemented, the second path corresponding to each page is pre-associated with the preset instructions of each page, which can be directly used in the actual interaction process to realize the voice interaction between the user and the web page. The preset instructions are used to operate the web page in the oil and gas station or oil depot scenario. Among them, the preset instructions of each page at least include: operation behavior and target object. For example, the operation behavior can be open, close, jump, etc., and the target object is at least the name of the page to be operated.
[0073] When step 103 is specifically implemented, after the path for executing each page is pre-associated with the preset instructions for operating each page, the page interaction system obtains the voice instructions issued by the user, and determines whether the above-mentioned page interaction system is in an activated state based on the voice instructions issued by the user. Only when the page interaction system is in an activated state can the page interaction system further identify the user's intention and execute accordingly.
[0074] In an optional embodiment of the present application, it is determined whether the page interaction system is in an activated state based on the voice command. The specific process is as follows: it is determined whether the acquired voice command contains an activation word, which is a preset specific word. Only when the specific word is recognized can the voice command be considered to contain the activation word. For example, the activation word can be a reduplicated word "Xiao Hong Xiao Hong". When "Xiao Hong Xiao Hong" is recognized, it is considered that the voice command contains the activation word. When the voice command contains the activation word, the page system can be activated.
[0075] In an optional embodiment of the present application, when the above-mentioned voice instruction includes the above-mentioned activation word, the volume of the above-mentioned voice instruction is further judged, that is, the volume of the voice instruction is compared with a preset volume, the preset volume is the lowest volume of the voice instruction recognizable by the page interaction system, and when the above-mentioned voice instruction includes the activation word and the volume of the above-mentioned voice instruction is greater than or equal to the preset volume, the state of the above-mentioned page interaction system is switched to an activated state.
[0076] In an optional embodiment of the present application, if the voice command does not contain an activation word, or the volume of the voice command is less than a preset volume, the above-mentioned page interaction system is in standby mode and does not perform any operation. This setting method can prevent the page interaction system from executing voice commands that are not related to page interaction, which can solve the problem of computing resources while more accurately executing the voice commands that the user actually wants to execute.
[0077] When step 104 is specifically implemented, when the page interaction system is in an activated state and the voice instruction contains a user intended word, the user intended word is matched with the preset instruction for similarity.
[0078] In an optional embodiment of the present application, after the page interaction system is in an activated state, it also includes: first, when the page interaction system is in an activated state, the voice instruction is sent to the edge voice recognition model, and the voice instruction is recognized as text to obtain the text information corresponding to the voice instruction; then the user intention word in the text information is obtained, and the user intention word is used to characterize at least one of the user's operation behavior and the operation object. The operation behavior is a word for executing the operation object, such as: open, close, jump, etc. The operation object is the target of the operation behavior, such as the page name, etc. If the voice instruction only contains the activation word, and the corresponding volume is less than the preset volume, the voice instruction is not sent to the edge voice recognition model for recognition, so as to ensure that only when the page interaction system is in an activated state and the volume of the voice instruction given by the user is greater than or equal to the preset volume, the voice instruction will be sent to the edge voice recognition model for recognition of the voice instruction, so as to avoid the waste of page system resources due to the recognition of invalid voice instructions, and save bandwidth and computing resources.
[0079] Exemplarily, when the page interaction system is not in an activated state, the voice commands issued by the user are recognized locally. After the activation word "Xiao Hong Xiao Hong" is recognized locally, if the volume of the voice command "Jump to XX homepage" after the activation word is less than the preset volume, the voice command will not be sent to the edge speech recognition model. Only when the volume of the voice command "Jump to XX homepage" after the activation word is greater than or equal to the preset volume, the above voice command will be sent to the edge speech recognition model for recognition.
[0080] When the step 105 is specifically implemented, all the similarities obtained by matching are judged against the preset threshold. When the similarity obtained by matching is greater than or equal to the preset threshold, the preset threshold is a preset similarity value. By setting the preset threshold, most preset instructions with low similarity can be excluded. The target instruction is determined based on the maximum similarity value, and the target instruction is the preset instruction corresponding to the maximum similarity. The following situations are included in the judgment of all the similarities obtained by matching and the preset threshold: when all the similarities obtained by matching are less than the preset threshold, the target instruction cannot be obtained at this time because the similarity between the user's intended word in the voice instruction and the preset instruction is too low; when there is a similarity greater than or equal to the preset threshold among all the similarities obtained by matching, the preset instruction corresponding to the maximum similarity is selected as the target instruction among the multiple similarities; when there are multiple similarities greater than or equal to the preset threshold among all the similarities obtained by matching, the preset instruction corresponding to the similarity is used as the target instruction. For example, the preset threshold can be set to values such as 0.6, 0.7, 0.8, and 0.9.
[0081] When step 106 is specifically implemented, when the target instruction is determined, the execution path is determined based on the target instruction, that is, the second path corresponding to the preset instruction corresponding to the maximum similarity is used as the execution path to execute the voice instruction. Since the execution path of each page in the webpage is changed to a global path in advance, the jump between pages of any level can be realized according to the preset instruction.
[0082] For example, the page interaction system is applied to the gas station system. The homepage includes sub-pages such as basic information, safe travel, equipment management, construction management, emergency management, marketing management, and system management. At this time, the gas station system is on the homepage. When the page interaction system is activated, the user issues a voice command "jump to inspection record". The page where "inspection record" is located is a sub-page of safe travel. The volume of the voice command is greater than the preset volume. The page interaction system recognizes the voice command and sends it to the edge voice recognition model to obtain the text information "jump to inspection record". The user intention word in the above text information is obtained, where the operation behavior is "jump" and the target object is "inspection record". The above user intention word is matched with the preset instruction by similarity, and the preset instruction corresponding to the maximum similarity value is used as the target instruction. The second path of the preset instruction corresponding to the maximum similarity value is obtained, and the target object "inspection record" is directly jumped from the homepage to the sub-page where the target object "inspection record" is located.
[0083] In an optional embodiment of the present application, after the page interaction system executes the above-mentioned voice instruction, the above-mentioned method also includes: the above-mentioned page interaction system will generate first result information for the executed instruction, and the first result information is used to indicate that the target instruction has been executed. The above-mentioned page interaction system responds to the generated first result information, and generates and plays the first voice feedback information based on the above-mentioned target instruction. For example, if the matched above-mentioned target instruction is "open the basic information page", the first voice feedback information generated based on the target instruction may be "the basic information page has been opened". After the playback is completed, the above-mentioned page interaction system maintains an activated state. When the page interaction system maintains an activated state, the voice command issued by the user can be re-recognized, and the corresponding instruction can be executed after voice recognition and user intention matching.
[0084] In an optional embodiment of the present application, the above-mentioned voice instruction is used to make the above-mentioned web page jump to the first page. After executing the above-mentioned voice instruction, when the above-mentioned page interaction system is in an activated state, a new voice instruction is obtained, and the above-mentioned new voice instruction is used to make the above-mentioned web page jump to the second page. The above-mentioned second page and the above-mentioned first page are pages of different levels in the above-mentioned hierarchical structure information; executing the above-mentioned new voice instruction makes the above-mentioned web page jump from the first page to the second page.
[0085] For example, if after executing the voice command, the gas station system is at the sub-page where the "inspection record" is located, and the new voice command issued by the user is "jump to employee information", after the same matching process as above, the page where the "employee information" is located is a sub-page under the basic information, and the page interaction system will execute the second path corresponding to the matched target command, and the web page will jump directly from the current "inspection record" sub-page to the "employee information" sub-page, without returning to the homepage from the current "inspection record" sub-page and then jumping to the "employee information" sub-page. In this way, it is possible to realize the jump between cross-module and multi-level pages, so as to achieve the purpose of randomly jumping between pages of different hierarchical structures according to the instructions, and realize convenient and efficient access.
[0086] In an optional embodiment of the present application, when the new voice command re-identified by the page interaction system is an invalid voice command and lasts for a preset time, the state of the page interaction system switches from an active state to an inactive state. The invalid voice command includes: the volume of the new voice command is less than the preset volume, or the new voice command cannot be recognized. The preset time can be set to an appropriate time such as 15 seconds. With an appropriate waiting time, it can not only meet the user's multiple command requirements, but also avoid wasting computing resources due to long waiting times.
[0087] In an optional embodiment of the present application, when the above-mentioned page interaction system is in an activated state, the method also includes the following process: if the acquired voice instruction does not contain the user's intended word, a second result information will be generated accordingly, and the second result information is used to indicate that the corresponding voice instruction cannot be executed. The page interaction system responds to the above-mentioned second result information and plays the corresponding second voice feedback information. After the playback is completed, the above-mentioned page interaction system maintains the activated state. Exemplarily, the second voice feedback information can be "did not hear clearly", or "please repeat", etc. Since in real scenarios, the user may issue an activation word to activate the page interaction system, and the acquired voice instruction sound is small or the acquired voice instruction only contains the operation behavior but not the target object, the page interaction system cannot recognize and execute the above-mentioned voice instruction. At this time, the page interaction system sends a second voice feedback information, which can achieve the purpose of reminding the user, further prompting the user to express his intention more accurately, and realize voice interaction with the web page.
[0088] In an optional embodiment of the present application, when the page interaction system maintains an activated state, the above method also includes: the page interaction system re-identifies a new voice instruction, and the new voice instruction includes an operation intention word; when the above operation intention word only represents the operation behavior, it is determined whether the above operation intention word is an exit intention word; the exit intention word is a word for exiting the page interaction system, such as "exit the system", "close all pages and exit", etc. In the case that the above operation intention word includes an exit intention, a third result information is generated, and the third result information is used to represent that the exit intention has been executed; the above page interaction system responds to the third result information based on the above exit intention and plays the third voice feedback information. Exemplarily, the third voice feedback information can be "Exit system completed".
[0089] In an optional embodiment of the present application, when the voice command issued by the user only contains an activation word but does not contain the user's intended word, the page interaction system will issue a corresponding fourth voice feedback message for the activation word to prompt the user to further issue a voice command containing the user's intended word. For example, the fourth voice feedback message can be "I'm here", "Please speak", etc., indicating that the page interaction system has been activated and is waiting for the user to issue a word containing the user's intention. In real scenarios, it may happen that after the user issues the activation word to activate the page interaction system, if the voice command issued by the user does not contain any operating behavior or target object, at this time, in order to encourage the user to interact with it, the page interaction system issues a fourth feedback message to prompt the user that the page system has been activated and can receive and execute voice commands at this time.
[0090] In an optional embodiment of the present application, if the target object in the voice command is a pop-up window, in order to avoid the situation where the pop-up window cannot be closed and thus affects the user experience, the above-mentioned page interaction system can execute the corresponding close command for the pop-up window. Specifically, first obtain the third path corresponding to each pop-up window contained in all pages, set the command to close each pop-up window as a preset close command, and associate the preset close command corresponding to each pop-up window with the third path, so that the page interaction system can directly close each pop-up window. When the above-mentioned page interaction system is in an activated state and the user's intention word is only represented as closing the pop-up window, the preset close command is executed based on the above-mentioned third path. For example, when the page interaction system is in an activated state, the voice command issued by the user is "Close the first pop-up window", and the above-mentioned page interaction system closes the first pop-up window according to the third path corresponding to the first pop-up window.
[0091] The embodiment of the present application proposes a page interaction method, which obtains the second path for operating each page in the web page, the second path is determined by the first path, the second path is the global path for operating each page, and the first path is the hierarchical path for operating each page; the second path corresponding to each page is associated with the preset instruction of each page, and the preset instruction is used to operate the web page in the oil and gas station or oil depot scene; obtains a voice instruction, and determines whether the page interaction system is in an activated state based on the voice instruction; when the page interaction system is in an activated state and the voice instruction contains a user intention word, the user intention word is matched with all preset instructions for similarity; when the similarity obtained by matching is greater than or equal to a preset threshold, the target instruction is determined, and the target instruction is the preset instruction corresponding to the maximum similarity; based on the second path corresponding to the preset instruction corresponding to the maximum similarity, the voice instruction is executed. The above method can realize the jump between pages of any level according to the preset instruction by seamlessly integrating the voice interaction function with the existing web page, so that users can use voice interaction very conveniently while greatly saving bandwidth and computing resources.
[0092] In a second aspect of the embodiment of the present application, a page interaction device is provided, wherein Figure 4 , Figure 4 : is a functional structure diagram of a page interaction device proposed in an embodiment of the present application, the device comprising:
[0093] A path acquisition module 401 is used to acquire a second path for operating each page in a webpage, wherein the second path is determined by the first path, the second path is a global path for operating each page, and the first path is a hierarchical path for operating each page;
[0094] An association module 402 is used to associate the second path corresponding to each page with a preset instruction of each page, wherein the preset instruction is used to operate a web page in a scenario of an oil and gas station or an oil depot;
[0095] A voice instruction acquisition module 403 is used to acquire a voice instruction and determine whether the page interaction system is in an activated state based on the voice instruction;
[0096] A matching module 404 is used to perform similarity matching between the user intended word and all preset instructions when the page interaction system is in an activated state and the voice instruction contains the user intended word;
[0097] The target instruction determination module 405 is used to determine the target instruction when the similarity obtained by matching is greater than or equal to a preset threshold, wherein the target instruction is the preset instruction corresponding to the maximum similarity;
[0098] The target execution module 406 is used to execute the voice instruction based on the second path corresponding to the preset instruction corresponding to the maximum similarity.
[0099] Wherein, the path acquisition module includes:
[0100] A hierarchical structure information acquisition submodule is used to acquire hierarchical structure information of pages at all levels in a webpage, and to operate a first path of each page, wherein the webpage is a webpage in a scenario of an oil and gas station or an oil depot;
[0101] The path changing submodule is used to generate horizontal structure information based on the hierarchical structure information, and change the first path to the second path based on the horizontal structure information.
[0102] Wherein, the voice command acquisition module includes:
[0103] A first judgment submodule, used to judge whether the voice instruction contains an activation word;
[0104] A second judgment submodule, configured to judge the volume of the voice instruction when the voice instruction includes the activation word;
[0105] The state switching submodule is used to switch the state of the page interaction system to an active state when the volume of the voice command is greater than or equal to a preset volume.
[0106] Wherein, the matching module includes:
[0107] A text recognition submodule, used for sending the voice command to the edge voice recognition model when the page interaction system is in an activated state, performing text recognition on the voice command, and obtaining text information corresponding to the voice command;
[0108] The user intention word acquisition submodule is used to acquire the user intention word in the text information, and the user intention word is used to characterize at least one of the user's operation behavior and the operation object.
[0109] Wherein, the device further comprises:
[0110] A first result information generating module, used to generate first result information, wherein the first result information is used to indicate that the target instruction is executed successfully;
[0111] A first result information response module, configured to generate and play first voice feedback information based on the target instruction in response to the first result information, and maintain an activated state;
[0112] The first re-recognition module is used to re-recognize a new voice command, and switch from an activated state to an inactivated state when the new voice command is an invalid voice command and lasts for a preset time. The invalid voice command includes: the volume of the new voice command is less than a preset volume, or the new voice command cannot be recognized.
[0113] Wherein, the device further comprises:
[0114] a re-acquisition module, used for acquiring a new voice command when the page interaction system is in an activated state, wherein the new voice command is used for causing the web page to jump to a second page, wherein the second page and the first page are pages of different levels in the hierarchical structure information;
[0115] The execution module is used to execute the new voice instruction to make the web page jump from the first page to the second page.
[0116] Wherein, the device further comprises:
[0117] A second result information acquisition module, configured to generate second result information when the voice instruction does not contain the user intended word, wherein the second result information is used to indicate that the corresponding voice instruction cannot be executed;
[0118] The second result information response module is used to respond to the second result information, play the corresponding second voice feedback information, and maintain the activation state.
[0119] Wherein, the device further comprises:
[0120] A second re-recognition module, used to re-recognize a new voice instruction, wherein the new voice instruction includes an operation intention word;
[0121] An exit intention recognition module, used to determine whether the operation intention word is an exit intention word when the operation intention word only represents an operation behavior;
[0122] A third result information generating module, configured to generate third result information when the operation intention word includes an exit intention, wherein the third result information is used to indicate that the exit intention has been executed;
[0123] A response module is used to respond to the third result information and play third voice feedback information based on the exit intention.
[0124] Wherein, the device further comprises:
[0125] A third path acquisition module, used to acquire the third path corresponding to each pop-up window contained in all pages;
[0126] A preset closing instruction setting module, used to set the command for closing each pop-up window as a preset closing instruction;
[0127] An association module, used to associate the preset closing instruction corresponding to each pop-up window with the third path;
[0128] A preset close instruction execution module is used to execute the preset close instruction based on the third path when the page interaction system is in an activated state and the user intention word is only characterized by closing the pop-up window.
[0129] Based on the same application concept, the embodiment of the present application discloses an electronic device in a third aspect. Figure 5 A schematic diagram of an electronic device disclosed in an embodiment of the present application is shown. Figure 5 As shown, the electronic device 100 includes: a memory 110 and a processor 120, the memory of the electronic device is not less than 12G, the main frequency of the processor is not less than 2.4GHz, the memory 110 and the processor 120 are connected via a bus communication, and a computer program is stored in the memory 110. The computer program can be run on the processor 120 to implement a page interaction method disclosed in an embodiment of the present application.
[0130] Based on the same application concept, the fourth aspect of the embodiment of the present application discloses a computer-readable storage medium, on which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, a page interaction method disclosed in the embodiment of the present application is implemented.
[0131] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0132] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, apparatuses, electronic devices, and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0135] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.
[0136] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.
[0137] The above is a detailed introduction to a page interaction method, device, equipment and medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A page interaction method, characterized in that: Applied to a page interaction system, the method includes: Acquire a second path for operating each page in the webpage, where the second path is determined by the first path, the second path is a global path for operating each page, and the first path is a hierarchical path for operating each page; Associating the second path corresponding to each page with a preset instruction of each page, wherein the preset instruction is used to operate a web page in a scenario of an oil and gas station or an oil depot; Acquire a voice command, and determine whether the page interaction system is in an activated state based on the voice command; When the page interaction system is in an activated state and the voice instruction contains a user intended word, the user intended word is matched with all preset instructions for similarity; When the similarity obtained by matching is greater than or equal to a preset threshold, determining a target instruction, wherein the target instruction is a preset instruction corresponding to the maximum similarity; The voice instruction is executed based on the second path corresponding to the preset instruction corresponding to the maximum similarity.
2. The page interaction method according to claim 1, characterized in that: Get the second path for operating each page in the web page, including: Obtaining hierarchical structure information of pages at all levels in a webpage, and a first path for operating each page, wherein the webpage is a webpage in a scenario of an oil and gas station or an oil depot; Based on the hierarchical structure information, horizontal structure information is generated, and based on the horizontal structure information, the first path is changed to the second path.
3. The page interaction method according to claim 1, characterized in that: Acquiring a voice command, and determining whether the page interaction system is in an activated state based on the voice command, includes: Determining whether the voice command contains an activation word; In the case where the voice instruction includes the activation word, determining the volume of the voice instruction; When the volume of the voice command is greater than or equal to a preset volume, the state of the page interaction system is switched to an activated state.
4. The page interaction method according to claim 1, characterized in that: After the page interaction system is in an activated state, it includes: When the page interaction system is in an activated state, the voice command is sent to an edge voice recognition model, and text recognition is performed on the voice command to obtain text information corresponding to the voice command; A user intention word in the text information is obtained, where the user intention word is used to characterize at least one of a user's operation behavior and an operation object.
5. The page interaction method according to claim 1, characterized in that: After executing the voice command, the method further includes: Generate first result information, where the first result information is used to indicate that the target instruction has been executed; In response to the first result information, generating and playing first voice feedback information based on the target instruction, and maintaining an activation state; Re-identify a new voice command, and switch from an active state to an inactive state if the new voice command is an invalid voice command and lasts for a preset time, wherein the invalid voice command includes: the volume of the new voice command is less than a preset volume, or the new voice command cannot be recognized.
6. The page interaction method according to claim 1, characterized in that: The voice command is used to make the webpage jump to the first page. After executing the voice command, the method further includes: When the page interaction system is in an activated state, obtaining a new voice command, wherein the new voice command is used to make the webpage jump to a second page, wherein the second page and the first page are pages of different levels in the hierarchical structure information; The new voice command is executed to cause the web page to jump from the first page to the second page.
7. The page interaction method according to claim 1, characterized in that: When the page interaction system is in an activated state, the method further includes: If the voice command does not include the user intended word, generating second result information, where the second result information is used to indicate that the corresponding voice command cannot be executed; In response to the second result information, the corresponding second voice feedback information is played and the activation state is maintained.
8. The page interaction method according to claim 6, characterized in that: In the case where the page interaction system remains in an activated state, the method further includes: Re-recognizing a new voice instruction, wherein the new voice instruction includes an operation intention word; In the case where the operation intention word only represents an operation behavior, determining whether the operation intention word is an exit intention word; In the case where the operation intention word includes an exit intention, generating third result information, wherein the third result information is used to indicate that the exit intention has been executed; In response to the third result information, third voice feedback information is played based on the exit intention.
9. The page interaction method according to claim 1, characterized in that: The method further comprises: Get the third path corresponding to each pop-up window contained in all pages; Set the command to close each pop-up window as the default close command; Correspondingly associating the preset closing instruction corresponding to each pop-up window with the third path; When the page interaction system is in an activated state and the user intention word is only characterized by closing the pop-up window, the preset closing instruction is executed based on the third path.
10. A page interaction device, characterized in that: The device comprises: A path acquisition module, used to acquire a second path for operating each page in a webpage, wherein the second path is determined by the first path, the second path is a global path for operating each page, and the first path is a hierarchical path for operating each page; An association module, used to associate the second path corresponding to each page with a preset instruction of each page, wherein the preset instruction is used to operate a web page in an oil and gas station or oil depot scenario; A voice instruction acquisition module, used to acquire voice instructions and determine whether the page interaction system is in an activated state based on the voice instructions; A matching module, configured to perform similarity matching between the user intended word and all preset instructions when the page interaction system is in an activated state and the voice instruction contains the user intended word; A target instruction determination module, used to determine a target instruction when the similarity obtained by matching is greater than or equal to a preset threshold, wherein the target instruction is a preset instruction corresponding to the maximum similarity; The target execution module is used to execute the voice instruction based on the second path corresponding to the preset instruction corresponding to the maximum similarity.
11. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the page interaction method according to any one of claims 1 to 9.
12. A computer-readable storage medium, characterized in that: A computer program / instruction is stored thereon, and when the computer program / instruction is executed by a processor, the page interaction method described in any one of claims 1-9 is implemented.
