CN118468890B - Menu navigation method, device, equipment, storage medium and product - Google Patents
Menu navigation method, device, equipment, storage medium and product Download PDFInfo
- Publication number
- CN118468890B CN118468890B CN202410941077.2A CN202410941077A CN118468890B CN 118468890 B CN118468890 B CN 118468890B CN 202410941077 A CN202410941077 A CN 202410941077A CN 118468890 B CN118468890 B CN 118468890B
- Authority
- CN
- China
- Prior art keywords
- menu
- node
- navigation
- information
- menu node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
本申请提供了一种菜单导航方法、装置、设备、存储介质及产品，其中，菜单导航方法包括：获取第一导航文本；将所述第一导航文本与第一菜单节点集合中各个菜单节点的节点信息进行匹配，并根据匹配结果在所述第一菜单节点集合中确定出多个候选菜单节点；根据各个候选菜单节点对应的节点信息对所述第一导航文本进行菜单节点意图识别，在各个候选菜单节点中确定出所述第一导航文本对应的目标菜单节点。本申请提出的技术方案，不仅支持用户的自然语言输入，降低了用户的学习成本和使用难度，还通过粗排检索和意图识别精确导航定位相结合的方式，大大降低了计算复杂性和耗时，提高了菜单导航的效率和准确性。
The present application provides a menu navigation method, device, equipment, storage medium and product, wherein the menu navigation method includes: obtaining a first navigation text; matching the first navigation text with the node information of each menu node in the first menu node set, and determining multiple candidate menu nodes in the first menu node set according to the matching results; performing menu node intent recognition on the first navigation text according to the node information corresponding to each candidate menu node, and determining the target menu node corresponding to the first navigation text in each candidate menu node. The technical solution proposed in the present application not only supports the user's natural language input, reduces the user's learning cost and difficulty of use, but also greatly reduces the computational complexity and time consumption by combining rough sorting retrieval with intent recognition and precise navigation positioning, and improves the efficiency and accuracy of menu navigation.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a menu navigation method, apparatus, device, storage medium, and product.
Background
With the continued development of information technology, various types of software, applications, and systems are equipped with complex menu structures to enable users to access a variety of functions and information. However, with the increase of complexity and hierarchy of menu structures, users often face difficulties in navigating, especially in applications with a large number of menu nodes and deep structures, users often need to repeatedly switch among multiple layers to find desired functions or information, which greatly reduces user experience.
The existing menu navigation method has limitations when processing complex menu structures and multi-level menu navigation. For example, some menu navigation methods rely on predefined keywords or fixed instruction modes, when a menu structure is complex, a user needs to memorize a large number of specific instructions to operate, so that the learning cost and the use difficulty of the user are increased. These problems seriously affect the user experience and reduce the efficiency and accuracy of menu navigation.
Disclosure of Invention
In view of this, embodiments of the present application are directed to providing a method, apparatus, device, storage medium, and product for menu navigation, which not only support natural language input of a user, but also reduce computation complexity and time consumption, and improve efficiency and accuracy of menu navigation.
According to a first aspect of an embodiment of the present application, there is provided a menu navigation method, including:
acquiring a first navigation text;
Matching the first navigation text with node information of each menu node in a first menu node set, and determining a plurality of candidate menu nodes in the first menu node set according to a matching result;
And carrying out menu node intention recognition on the first navigation text according to node information corresponding to each candidate menu node, and determining a target menu node corresponding to the first navigation text in each candidate menu node.
Optionally, the method further comprises:
Acquiring historical interaction information of the first navigation text;
the menu node intention recognition is carried out on the first navigation text according to the node information corresponding to each candidate menu node, and the target menu node corresponding to the first navigation text is determined in each candidate menu node, which comprises the following steps:
And carrying out menu node intention recognition on the first navigation text according to node information corresponding to each candidate menu node and the historical interaction information, and determining a target menu node corresponding to the first navigation text in each candidate menu node.
Optionally, the identifying the menu node intention of the first navigation text according to the node information corresponding to each candidate menu node and the history interaction information, and determining the target menu node corresponding to the first navigation text in each candidate menu node includes:
Generating a task instruction according to node information corresponding to each candidate menu node, the historical interaction information and the first navigation text, wherein the task instruction is used for indicating an object receiving the task instruction to identify the menu node intention of the first navigation text according to the node information corresponding to each candidate menu node and the historical interaction information, and determining a target menu node corresponding to the first navigation text in each candidate menu node;
And inputting the task instruction into a pre-trained large language model, executing the task instruction by the pre-trained large language model, and determining a target menu node corresponding to the first navigation text from all candidate menu nodes.
Optionally, the matching the first navigation text with node information of each menu node in the first menu node set, and determining a plurality of candidate menu nodes in the first menu node set according to a matching result, includes:
matching the first navigation text with node information of each menu node in a first menu node set, and determining the matching degree between the first navigation text and the node information of each menu node in the first menu node set;
and determining a preset number of candidate menu nodes in the first menu node set according to the matching degree between the first navigation text and the node information of each menu node in the first menu node set.
Optionally, the method further comprises:
Generating prompt information under the condition that a target menu node corresponding to the first navigation text is not determined in all candidate menu nodes, wherein the prompt information is used for prompting a user to input supplementary navigation information;
and/or the number of the groups of groups,
And determining a target navigation path according to the target menu node, wherein the target navigation path comprises a navigation path from the current menu node to the target menu node.
Optionally, the matching includes keyword matching and/or semantic similarity matching, and the node information includes node name and/or node description information.
Optionally, the node information further includes entity information associated with the menu node, and/or navigation text examples corresponding to the menu node, where the entity information includes at least one of an entity name, an entity alias, and entity description information.
According to a second aspect of an embodiment of the present application, there is provided a menu navigation apparatus including:
The first unit is used for acquiring a first navigation text;
The second unit is used for matching the first navigation text with the node information of each menu node in the first menu node set, and determining a plurality of candidate menu nodes in the first menu node set according to a matching result;
and the third unit is used for carrying out menu node intention recognition on the first navigation text according to the node information corresponding to each candidate menu node, and determining the target menu node corresponding to the first navigation text in each candidate menu node.
According to a third aspect of embodiments of the present application, there is provided an electronic device comprising a memory and a processor;
the memory is connected with the processor and used for storing programs;
The processor is configured to implement the menu navigation method according to any one of the first aspect of the embodiments of the present application by running the program in the memory.
According to a fourth aspect of embodiments of the present application, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements a menu navigation method according to any one of the first aspects of embodiments of the present application.
According to a fifth aspect of embodiments of the present application, there is provided a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to implement a menu navigation method as in any of the first aspects of embodiments of the present application.
The menu navigation method comprises the steps of firstly obtaining a first navigation text, then matching the first navigation text with node information of each menu node in a first menu node set, determining a plurality of candidate menu nodes in the first menu node set according to a matching result, finally identifying the intention of the menu nodes of the first navigation text according to the node information corresponding to each candidate menu node, and determining a target menu node corresponding to the first navigation text in each candidate menu node.
The menu navigation method provided by the application has the advantages that on one hand, the natural language input of a user is supported without depending on a predefined keyword or a fixed instruction mode, the learning cost and the use difficulty of the user are reduced, on the other hand, a plurality of candidate menu nodes are confirmed by carrying out preliminary quick matching on the first navigation text and the menu nodes in the first menu node set, the range of the intention recognition of the subsequent menu nodes is greatly reduced, and when the intention recognition of the menu nodes is carried out, only the candidate menu determined by the preliminary matching is considered, so that the calculation complexity and the time consumption are greatly reduced, the navigation efficiency is improved, and the accuracy of the menu navigation is also improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of a menu navigation system according to an embodiment of the present application.
Fig. 2 is a flowchart of a first menu navigation method according to an embodiment of the present application.
Fig. 3 is a flowchart of a second menu navigation method according to an embodiment of the present application.
Fig. 4 is a schematic process flow diagram of determining a target menu node corresponding to a first navigation text from among candidate menu nodes according to an embodiment of the present application.
Fig. 5 is a flowchart of a third menu navigation method according to an embodiment of the present application.
Fig. 6 is a schematic structural diagram of a menu navigation device according to an embodiment of the present application.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical scheme of the embodiment of the application is suitable for being applied to various scenes needing menu navigation, in particular to application scenes with complex and multi-level menu systems, such as mobile banking, intelligent home, vehicle-mounted systems, self-service customer service scenes and the like, under the scenes, a user usually needs to quickly and accurately locate required functions or information.
The technical scheme provided by the embodiment of the application can be exemplarily applied to hardware equipment such as a processor, electronic equipment, a server (comprising a cloud server) and the like, or packaged into a software program to be operated, and when the hardware equipment executes the processing procedure of the technical scheme of the embodiment of the application, or the software program is operated, the purpose of automatically splitting a target task and automatically calling an application program interface required by the task can be realized, so that the target task is completed. The embodiment of the application only exemplary introduces the specific processing procedure of the technical scheme of the application, but does not limit the specific implementation form of the technical scheme of the application, and any technical implementation form capable of executing the processing procedure of the technical scheme of the application can be adopted by the embodiment of the application.
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Before describing the scheme of the application, the related technology is first described:
With the continued development of information technology, various types of software, applications, and systems are equipped with complex menu structures to enable users to access a variety of functions and information. However, with the increase of complexity and hierarchy of menu structures, users often face difficulties in navigating, especially in applications with a large number of menu nodes and deep structures, users often need to repeatedly switch among multiple layers to find desired functions or information, which greatly reduces user experience.
The existing menu navigation method has limitations when processing complex menu structures and multi-level menu navigation. For example, some menu navigation methods rely on predefined keywords or fixed instruction patterns, when a menu structure is complex, a user needs to memorize a large number of specific instructions to operate, so that the learning cost and the use difficulty of the user are increased. These problems seriously affect the user experience and reduce the efficiency and accuracy of menu navigation.
In view of this, embodiments of the present application provide a method, apparatus, device, storage medium, and product for menu navigation, which not only supports natural language input of a user, but also reduces computation complexity and time consumption, and improves efficiency and accuracy of menu navigation, and detailed description is provided in the following embodiments.
Exemplary System
For easy understanding, first, an implementation environment of the menu navigation method provided by the embodiment of the present application is described in an exemplary manner, please refer to fig. 1, fig. 1 is a schematic structural diagram of a menu navigation system, and the menu navigation method provided by the present application may be applied to the menu navigation system in an exemplary manner.
As shown in fig. 1, the menu navigation system includes an instruction acquisition module 110, a processor 120, and an output module 130, where the processor 120 is communicatively connected to the instruction acquisition module 110 and the output module 130, respectively.
The instruction obtaining module 110 is configured to receive a navigation instruction input of a user, and send the received navigation instruction to the processor 120 through a communication network.
The instruction acquisition module 110 may be a voice input component or a text input component. The voice input component may be any functional component capable of supporting the user to perform voice input, for example, may be a microphone, a pickup, etc., and the specific processing procedure of voice acquisition may be referred to as implementation procedure of the conventional technology. The text input component may be any functional component capable of supporting the user to input text, for example, may be a touch screen, a keyboard, etc., and the specific text acquisition processing procedure may be referred to as implementation procedure of conventional technology.
The processor 120 is configured to execute the menu navigation method provided by the embodiment of the present application after obtaining the navigation instruction sent by the instruction obtaining module 110, specifically, first obtain a first navigation text, then match the first navigation text with node information of each menu node in a first menu node set, determine a plurality of candidate menu nodes in the first menu node set according to a matching result, and finally identify a menu node intention of the first navigation text according to node information corresponding to each candidate menu node, and determine a target menu node corresponding to the first navigation text in each candidate menu node. As for other specific implementations of the menu navigation method, specific developments will be described in the following, and will not be described in detail here.
It should be noted that, when the instruction obtaining module 110 is a text input component, the navigation instruction received by the processor 120 is a text instruction, and the navigation instruction is a first navigation text, and when the instruction obtaining module 110 is a voice input component, the navigation instruction received by the processor 120 is a voice instruction, and the first navigation text is a transcription text of the voice instruction.
The processor 120 may be various types of processing devices, and the specific type of the processing device is determined according to the scale, application scenario and performance requirement of the menu navigation system, and may be an independent server, a server group formed by a plurality of physical servers, a cloud server for providing cloud computing service, and the like.
The output module 130 is configured to display information corresponding to the target menu node determined by the processor 120 to a user, or perform a corresponding operation according to the target menu node, for example, skip to a corresponding functional interface, play related multimedia content, etc. Meanwhile, the output module 130 may also be used to provide feedback to the user, such as a voice prompt, a text prompt, or a graphical interface prompt, so as to enhance the user interaction experience.
By way of example, the output module 130 may be a display screen, speaker, or like output device for communicating information to a user in visual or audible form.
Exemplary method
Fig. 2 is a flowchart of a first voice navigation method according to an embodiment of the present application. As shown in fig. 2, the voice navigation method provided in this embodiment includes steps S201 to S203:
S201, acquiring a first navigation text.
The first navigation text may be understood as a text instruction for navigating in a menu navigation system, typically comprising a description of a desired menu item or function by a user, capable of embodying the user's intention.
Alternatively, the first navigation text may include, but is not limited to, menu node names, function descriptions or requirements, keywords or phrases, natural language instructions, and the like. For example, "i am saving card lost a need to grasp to handle loss", "please open the device menu", "how to change the password", "i am want to view account information", "please bring me to the shopping cart", and "i am how to modify my shipping address", etc.
Optionally, the acquiring the first navigation text includes that a text input component of the menu navigation system receives the first navigation text input by the user and sends the first navigation text to the processor, and the processor can acquire the first navigation text.
Optionally, the acquiring the first navigation text includes that the voice input component of the menu navigation system receives a first navigation voice input by a user and sends the first navigation voice to the processor, and the processor performs voice recognition on the first navigation voice after receiving the first navigation voice to acquire a transcription text of the first navigation voice, namely the first navigation text. As for the specific content of the speech recognition, it can be realized with reference to the related art, and the present application is not limited thereto.
Optionally, the obtaining the first navigation text includes the processor receiving the first navigation text sent by other applications or services.
S202, matching the first navigation text with node information of each menu node in a first menu node set, and determining a plurality of candidate menu nodes in the first menu node set according to a matching result.
A menu node may be understood as an independent unit in menu navigation, and is usually represented as a clickable item or link, which may be a top-level menu node or a submenu node nested under the top-level menu node. For example, in a navigation menu of a financial system, debit card charging and loss, debit card loss, electronic payment, payment settlement, account management, account details, business information changes, help centers, contact customer service, etc. may all be considered menu nodes.
The first set of menu nodes may be understood as a predefined set of menu nodes in the menu navigation system for building a navigation structure, each menu node representing a different functional area, information classification or operation portal.
Optionally, the first set of menu nodes includes all menu nodes in the menu navigation system. In an exemplary menu navigation system of an e-commerce website, a first menu node set comprises top-level menu nodes such as a first page, commodity classification, shopping cart, my order, and the like, each top-level menu node may comprise a plurality of sub-menu nodes, the sub-menu nodes also belong to the first menu node set, for example, sub-menu nodes such as electronic products, household articles, clothing shoes and caps, and the like, and further sub-menu nodes may also comprise sub-menu nodes which are more subdivided, and also belong to the first menu node set, for example, sub-nodes such as mobile phones, computers, cameras, and the like.
Node information of a menu node may be understood as information associated with the menu node, typically containing element information describing and identifying features of the menu node, to aid in understanding the menu node content and functionality.
Optionally, the node information of the menu node includes a node name and/or node description information.
The node name is a direct identification of the menu node, and can help quickly identify functions and contents of the menu node, such as debit card loss, card swallowing, account adjustment, enterprise information change and the like.
The node description information provides a more detailed description of the menu node functionality, helping to further illustrate the node names, which may include the specifics of the node, the category to which it belongs, the usage scenario, etc. For example, the description information of the "debit card loss" node may be "after a card of a bank is lost, the loss is performed at a counter or a telephone", the description information of the "swallow card and reconciliation" node may be "related to the POS machine or ATM equipment for swallow card and accounting reconciliation processing", and the description information of the "enterprise information change" node may be "service that an enterprise needs to update bank account data due to change information".
Optionally, the node information of the menu node may further include entity information, node ID, father node ID, navigation path, and the like associated with the menu node, which can help locate the menu node, which is not limited in the present application.
It should be noted that, before executing the menu navigation method provided by the present application, the first menu node set and the node information of the menu nodes in the first menu node set have been set and stored in advance, and when executing the menu navigation method provided by the present application, the processor may directly call the preset first menu node set and the node information of each menu node in the first menu node set.
Optionally, the first navigation text is matched with node information of each menu node in the first menu node set, and a plurality of candidate menu nodes are determined in the first menu node set according to a matching result, including steps A1-A2:
a1, matching the first navigation text with node information of each menu node in a first menu node set, and determining the matching degree between the first navigation text and the node information of each menu node in the first menu node set.
Specifically, after the first navigation text is obtained, the processor invokes node information of each menu node in the preset first menu node set, and performs first matching on the first navigation text and the node information of each menu node in the first menu node set, so that the matching degree of the first navigation text and the node information of each menu node in the first menu node set can be obtained.
The matching degree can be understood as a degree of similarity or a degree of association between the first navigation text and node information of each menu node in the first menu node set, and is used for quantifying the degree of coincidence between the first navigation text and each menu node.
Alternatively, the first matching may be performed by a single matching algorithm, or a combination of multiple matching algorithms may be used. When the first matching adopts a single matching algorithm, the matching degree calculated by the matching algorithm is the matching degree of the first matching. When the first matching adopts a combination of a plurality of matching algorithms, the matching degree calculated by each matching algorithm is subjected to mathematical operations such as weighting calculation and the like, and the matching degree of the first matching can be obtained.
Alternatively, the first match may be any one or a combination of two of keyword match and semantic similarity match.
Keyword matching can be understood as comparing the occurrence of keywords in the node information of the first navigation text and each menu node, and according to the comparison result, the matching degree between the first navigation text and the node information of each menu node can be determined.
The semantic similarity matching can be understood as comparing the meaning similarity degree between the first navigation text and the node information of each menu node, and according to the comparison result, the matching degree between the first navigation text and the node information of each menu node can be determined.
The keyword matching and the semantic similarity matching are combined, so that the efficiency, the flexibility and the robustness of the first matching can be considered, and the matching result of the first matching is more accurate.
The specific implementation manners of keyword matching, semantic similarity matching and weighting calculation can be realized by referring to the related prior art, and the application is not described in detail.
A2, determining a preset number of candidate menu nodes in the first menu node set according to the matching degree between the first navigation text and the node information of each menu node in the first menu node set.
Optionally, after determining the matching degree between the first navigation text and the node information of each menu node in the first menu node set, selecting, from the first menu node set, a preset number of menu nodes with highest matching degree as candidate menu nodes according to the sequence from high matching degree to low matching degree. The menu navigation system includes 100 menu nodes in total, that is, the first menu node set includes 100 menu nodes, and when the preset number is set to 10, the candidate menu nodes finally determined are 10 menu nodes with highest matching degree.
Optionally, after determining the matching degree between the first navigation text and the node information of each menu node in the first menu node set, selecting all menu nodes with matching degree greater than a preset matching degree threshold as candidate menu nodes.
According to the above, it can be determined that the higher the matching degree of the node information of the first navigation text and the menu node, the higher the matching degree between the first navigation text and the menu node, the greater the possibility that the target menu node corresponding to the first navigation text is the menu node, and therefore, the candidate menu node includes a plurality of menu nodes which are most matched with the target menu node corresponding to the first navigation text in the first menu node set.
It should be noted that, the number of candidate menu nodes and the specific value of the preset matching threshold are determined according to the actual application scenario, which is not limited by the present application.
Optionally, after determining the candidate menu node, the candidate menu node may be further subjected to optimization processing, for example, the ranking of the candidate menu may be adjusted and optimized through a user feedback loop, so as to better conform to the actual needs and preferences of the user.
S203, carrying out menu node intention recognition on the first navigation text according to node information corresponding to each candidate menu node, and determining a target menu node corresponding to the first navigation text in each candidate menu node.
The target menu node may be understood as a menu node that the user desires to access through the current input.
The menu node intention recognition of the first navigation text may be understood as analyzing the first navigation text to determine the access intention of the first navigation text to the menu node.
Optionally, conventional intention recognition technology may be adopted to perform intention recognition on the first navigation text, determine a recognition result of the intention recognition, then perform deep matching on the result of the intention recognition and node information corresponding to each candidate menu node, determine a matching degree corresponding to each candidate menu node, and select a candidate menu node with the highest matching degree as a target menu node.
Further, when the first navigation text is subjected to intention recognition, not only the first navigation text per se but also node information of each candidate menu node are comprehensively considered. When the intention is identified for the first navigation text, the node information of the candidate menu nodes can provide semantic and contextual support for the first navigation text, so that the processor is helped to better understand the specific meaning of the first navigation text in a specific scene, and the intention of the user query can be accurately understood.
As an alternative implementation manner, the node information of the menu node may further include entity information associated with the menu node, where the entity information includes at least one of an entity name, an entity alias, and entity description information.
Entity information associated with a menu node may be understood as information about a particular business object or data model represented in the menu node.
Illustratively, the menu node is "debit card loss," the entity name of the entity associated with the menu node is "debit card," the entity is named "bank card, deposit card, magnetic stripe card, chip card, etc," and the entity description information is "card issuing bank issues to cardholder, there is no credit line, and the cardholder deposits first and then uses the bank card.
Upon menu node intent recognition of the first navigation text, entity information associated with the candidate menu node may provide richer semantic and contextual support for the first navigation text. In one aspect, the entity alias provides additional entity keywords, and illustratively, if a particular product or service name is mentioned in the first navigation text that happens to match an associated entity name or alias for a menu node, the system can more confidently determine that the user's intent is to access the menu node. On the other hand, the entity description information provides detailed descriptions about functions and characteristics of the entity for the system, and if the first navigation text is ambiguous in description of the entity, for example, a preset entity name and entity alias are not used, but the description of the entity is matched with the preset entity description information, the system can determine the entity according to the entity description information, and further determine the intention of the user.
As an alternative implementation manner, the node information of the menu node may further include a navigation text example corresponding to the menu node.
The navigation text example corresponding to a menu node can be understood as a navigation text example of which a target menu node is the menu node, and is generally closely related to the function or content of the menu node, and can be regarded as typical navigation text possibly input by a user.
The method comprises the steps of taking a menu node as a debit card loss report, taking a navigation text example corresponding to the menu node as a My card lost carelessly and needing loss report, taking a menu node as an enterprise information change, and taking a navigation text example corresponding to the menu node as an account opening line information of a change me company.
Examples of navigation text corresponding to candidate menu nodes will provide additional references to the intent recognition process when performing menu node intent recognition on the first navigation text. For example, by comparing the first navigation text with the navigation text examples of each candidate menu node, an additional, more direct reference point can be provided for the processor, which is helpful for reducing misjudgment and ambiguity, and helping the processor to better determine the user's menu node intention.
Specifically, after determining a plurality of candidate menu nodes with highest matching degree with the first navigation text, the processor executes a first strategy, analyzes the first navigation text by using node information corresponding to the candidate menu nodes, and determines the real intention of the user, namely, determines the target menu node which the user wants to access and operate.
There are a number of implementations of the first strategy. Optionally, the first policy is implemented based on a model-based processing concept. And training an intention recognition model in advance, and inputting node information corresponding to each candidate menu node and the first navigation text into the intention recognition model to obtain the target menu node. The trained intention recognition model can recognize the intention of the first navigation text according to the node information corresponding to each candidate menu node, and determines the target menu node corresponding to the first navigation text in each candidate menu node.
Furthermore, the first strategy can be implemented by using a pre-trained large language model, and the accuracy of the intention recognition can be further improved by using the powerful language processing capability and matching capability of the large language model, which will be specifically developed in the following matters and will not be described in detail here.
The menu navigation method provided by the application has the advantages that on one hand, the natural language input of a user is supported without depending on a predefined keyword or a fixed instruction mode, the learning cost and the use difficulty of the user are reduced, on the other hand, a plurality of candidate menu nodes are confirmed by carrying out preliminary quick matching on the first navigation text and the menu nodes in the first menu node set, the range of the intention recognition of the subsequent menu nodes is greatly reduced, and when the intention recognition of the menu nodes is carried out, only the candidate menu determined by the preliminary matching is considered, so that the calculation complexity and the time consumption are greatly reduced, the navigation efficiency is improved, and the accuracy of the menu navigation is also improved.
Fig. 3 is a flow chart of a second menu navigation method according to an embodiment of the present application, as shown in fig. 3, the menu navigation method provided in this embodiment includes steps S301 to S304:
s301, acquiring a first navigation text.
S302, matching the first navigation text with node information of each menu node in a first menu node set, and determining a plurality of candidate menu nodes in the first menu node set according to a matching result.
The content of step S301 corresponds to the content of step S201 in the foregoing embodiment, the content of step S302 corresponds to the content of step S202 in the foregoing embodiment, and the specific content of steps S301 and S302 may be referred to the content of the embodiment shown in fig. 2, which is not repeated here.
S303, acquiring history interaction information of the first navigation text.
The historical interaction information can be understood as interaction information of the user and the menu navigation system before the dialogue. Optionally, the historical interaction information includes a data record generated when the user interacts with the menu navigation system within a preset time period in the past. Optionally, the history interaction information includes a preset number of interaction data records of the user and the menu navigation system before the current dialogue and with the shortest time interval from the current dialogue.
Optionally, the historical interaction information comprises multiple rounds of historical dialogue information of a current session of the user with the menu navigation system.
The multi-round history dialogue of the current session can provide semantic content, context information and context information associated with the first navigation text for the first navigation text, so that the processor can be helped to better understand the content expressed by the first navigation text, more accurately identify the menu node intention corresponding to the first navigation text, and provide additional data points for the system when facing the diversity of user input, so that the processor can process various input conditions more robustly. For example, the first navigation text is "how to modify", and if the user mentions in the history dialog of the current session that the user wants to view the status of the order, the processor may infer in connection with the history dialog that the user may want to know how to modify the order, rather than other unrelated operations.
Optionally, the historical interaction information includes historical behavior of the user including, but not limited to, a combination of one or more of menu nodes accessed by the user, dwell times, operation paths, search queries, click behaviors.
The historical behaviors of the user can reflect the behavior habits and preferences of the user, and through analysis of the historical behaviors, the processor can learn and memorize the behavior patterns and preferences of the user, so that when the menu node intention recognition is carried out on the first navigation text, the behavior patterns and preferences of the user are used as the basis for auxiliary judgment. For example, when the first navigation text is ambiguous, contains a plurality of intents, and is insufficient to explicitly point to a candidate menu node, the processor may assist in determining and determining the most likely target menu node in combination with the user's behavior pattern and preferences, thereby providing more personalized and accurate services to the user.
In sum, the historical interaction information can help the processor to more comprehensively understand the user demands, so that the navigation intention of the user is more accurately identified, and the user experience is improved.
S304, carrying out menu node intention recognition on the first navigation text according to node information corresponding to each candidate menu node and the historical interaction information, and determining a target menu node corresponding to the first navigation text in each candidate menu node.
Specifically, after determining a plurality of candidate menu nodes in a first menu node set and acquiring historical interaction information of a first navigation text, the processor invokes node information corresponding to each preset candidate menu node, performs comprehensive analysis on the historical interaction information of the first navigation text, the node information corresponding to each candidate menu node and the first navigation text, and performs menu node intention recognition on the first navigation text according to the historical interaction information of the first navigation text, the node information corresponding to each candidate menu node and the first navigation text together, and determines a candidate menu node which is most matched with the intention of the first navigation text from the plurality of candidate menu nodes as a target menu node.
Further, a pre-trained large language model may be employed to enable menu node intent recognition of the first navigation text. As an alternative implementation, as shown in fig. 4, step S304 includes steps S401-S402:
s401, generating a task instruction according to node information corresponding to each candidate menu node, the historical interaction information and the first navigation text, wherein the task instruction is used for indicating an object receiving the task instruction to identify the menu node intention of the first navigation text according to the node information corresponding to each candidate menu node and the historical interaction information, and determining a target menu node corresponding to the first navigation text in each candidate menu node.
The task instruction may be a sentence, a question or a combination of a series of instructions, and the specific content and format of the task instruction are not limited in the present application.
Optionally, the task instruction includes node information, history interaction information and a first navigation text corresponding to each candidate menu node.
Optionally, the task instruction includes node information, history interaction information, a first navigation text and a task description text corresponding to each candidate menu node, where the task description text may be understood as text content describing the task, so that an object receiving the task instruction specifies the task.
Further, according to a preset task instruction format, combining contents included in the task instruction to obtain the task instruction. The task instruction format is used for defining the structure and the representation method of the task instruction, is preset and stored on the controller or server side, and can be directly called for use when needed. The task instruction format is determined according to the actual application scene and the requirements, and the application is not limited to the task instruction format.
Illustratively, the specific content of one task instruction is as follows:
Prompt, suppose you are an intelligent interactive assistant, please determine the target menu node of the first navigation text in the candidate menu nodes according to the node information and the history interaction information of the given candidate menu node. The requirement is that 1, the answer is output according to json form of [ { "target menu node" } ], 2, if there is no proper target menu node in the candidate menu nodes, the predicted target menu node is "other"
# First navigation text, troublesome grasp handling loss reporting
Node information of # candidate menu node { "debit card loss reporting": "desc: after the card of the bank is lost, loss reporting is performed at the counter or phone; example, my card is carelessly lost, loss is required, enterprise information change is required, desc is a service that an enterprise needs to update bank account information due to change information, example is a service that changes account opening information of an enterprise company, and is required to be reported
Node information of # candidate menu node { alias: deposit card, desc: cardholder deposit first, then used bank card }
# Historical interaction information: { user: "how is your credit card lost? customer service" you good, regrettably hear you that the savings card is lost. To ensure your funds safety, you are advised to transact loss as soon as possible }
S402, inputting the task instruction into a pre-trained large language model, executing the task instruction by the pre-trained large language model, and determining a target menu node corresponding to the first navigation text from all candidate menu nodes.
The large language model (Large language model, LLM) refers to a generated deep neural network model based on a transducer structure, and has strong natural language processing capability. It should be noted that any large language model may be used in the embodiments of the present application.
The embodiment of the application needs to train a large language model in advance. Specifically, a data set formed by a plurality of groups of task instructions and target menu nodes is used as a training sample to pretrain the existing large language model, so that the trained large language model can execute task instructions, namely tasks corresponding to the task instructions, and the menu node intention recognition is carried out on the first navigation text according to node information corresponding to each candidate menu node and historical interaction information, and the target menu node corresponding to the first navigation text is determined in each candidate menu node.
Specifically, after a task instruction is generated, the generated task instruction is input into a pre-trained large language model, the large language model executes the task instruction, menu node intention recognition is performed on the first navigation text according to node information corresponding to each candidate menu node and history interaction information, and a target menu node corresponding to the first navigation text is output.
Therefore, by means of excellent natural language processing capability and matching capability of the pre-trained large language model, node information, history interaction information and first navigation text corresponding to each candidate menu node can be comprehensively and accurately understood, task description text can be deeply understood, and more accurate menu node intention recognition can be performed on the first navigation text by comprehensively considering multiparty factors on the basis.
Moreover, the scheme has applicability to any scene, and the target menu node corresponding to the first navigation text can be determined by means of the super-strong capability of the large language model only by acquiring the first navigation text, the historical interaction information of the first navigation text and the node information corresponding to each candidate menu node, so that the scheme has higher universality.
Fig. 5 is a flowchart of a third menu navigation method according to an embodiment of the present application, as shown in fig. 5, where the menu navigation method provided in the embodiment includes steps S501 to S505:
s501, acquiring a first navigation text.
S502, matching the first navigation text with node information of each menu node in a first menu node set, and determining a plurality of candidate menu nodes in the first menu node set according to a matching result.
S503, carrying out menu node intention recognition on the first navigation text according to node information corresponding to each candidate menu node, and judging whether a target menu node corresponding to the first navigation text is determined in each candidate menu node.
The content of step S501 corresponds to the content of step S201 in the foregoing embodiment, the content of step S502 corresponds to the content of step S202 in the foregoing embodiment, the content of step S503 corresponds to the content of step S203 in the foregoing embodiment, and the specific content of steps S501-S503 can be referred to the content of the embodiment shown in fig. 2, which is not repeated here.
In step S503, if the target menu node corresponding to the first navigation text is determined in each candidate menu node, step S504 is executed, and if the target menu node corresponding to the first navigation text is not determined in each candidate menu node, step S505 is executed.
S504, determining a target navigation path according to the target menu node, wherein the target navigation path comprises a navigation path from the current menu node to the target menu node.
Optionally, the navigation path of each menu node is preset and stored, and after the target menu node is determined, the navigation path from the current menu node to the target menu node, that is, the target navigation path, can be calculated according to the preset navigation path of the target menu node and the navigation path of the current menu node.
Optionally, the hierarchical structure of the navigation menu and the parent-child relationships of the menu nodes are preset and stored, and after the target menu node is determined, the navigation path from the current menu node to the target menu node, namely the target navigation path, can be automatically calculated according to the hierarchical structure of the preset navigation menu and the parent-child relationships of the menu nodes.
Optionally, when calculating the target navigation path, the optimal target navigation path is determined in consideration of the minimization of the number of clicks of the user and/or a shortcut (such as a direct voice command or a shortcut menu option), so as to directly guide the user to reach the target menu node.
Optionally, determining the operation habit of the user according to the historical interaction information of the user, and when determining the target navigation path, considering the operation habit of the user to generate a navigation path which is more familiar and satisfactory to the user.
Further, after the target navigation path is determined, the menu navigation system generates reply information to the first navigation text according to the navigation path, wherein the reply information can be voice information or text information, and comprises a next operation prompt for the user, so that the user can be clearly guided to go to the target menu node through voice input or text input or clicking operation. For example, the reply message may be "I have helped you locate to loss services, please say 'go to loss', or click on continue here".
Further, when the user encounters difficulty in requesting help in the navigation process, the menu navigation system can provide corresponding support. For example, if the user indicates "I do not know what to do," the menu navigation system may provide more detailed step descriptions or direct contact customer service support.
Based on the above, the menu navigation system not only ensures that the user can efficiently reach the target service, but also improves the overall user experience through dynamic feedback and continuous optimization. The intelligent navigation method can adapt to the behavior modes of different users by utilizing big data and machine learning technology, is continuously self-perfected, and ensures that optimal user support and service are provided.
S505, under the condition that the target menu node corresponding to the first navigation text is not determined in the candidate menu nodes, prompting information is generated, and the prompting information is used for prompting a user to input supplementary navigation information.
When the first navigation text content is too fuzzy, the first navigation text content is seriously incomplete, various special conditions such as various interpretations of the first navigation text exist, the first navigation text is input in error or a menu structure is updated, the processor may not be able to determine the target menu node of the first navigation text in the candidate menu nodes, in which case, in order to promote user experience and help the user to complete target operation, the menu navigation system will generate prompt information to guide the user to input supplementary navigation information, so that the system can determine the target menu node of the user according to the supplementary navigation information input by the user.
For example, the prompt may be "you input is blurred," please provide more specific navigation instructions, for example, "view user information" or "browse order record'" "set" may relate to various aspects, please indicate specific content that you want to set, such as "network set", "account set" or "privacy set", etc. "you input is wrong, please check spelling or grammar, and reenter your navigation instructions", etc. Through the prompt information, a user can be guided to gradually and definitely determine the self navigation requirement, and finally, the supplementary navigation information is easier to identify by input.
Exemplary apparatus
Corresponding to the menu navigation method, the embodiment of the application also provides a menu navigation device. Fig. 6 is a schematic structural diagram of a menu navigation apparatus according to an embodiment of the present application, where, as shown in fig. 6, the menu navigation apparatus according to an embodiment of the present application includes:
A first unit 601, configured to obtain a first navigation text;
A second unit 602, configured to match the first navigation text with node information of each menu node in a first menu node set, and determine a plurality of candidate menu nodes in the first menu node set according to a matching result;
and a third unit 603, configured to identify a menu node intention of the first navigation text according to node information corresponding to each candidate menu node, and determine a target menu node corresponding to the first navigation text in each candidate menu node.
The menu navigation device provided by the application has the advantages that on one hand, the natural language input of a user is supported without depending on a predefined keyword or a fixed instruction mode, the learning cost and the use difficulty of the user are reduced, on the other hand, a plurality of candidate menu nodes are confirmed by carrying out preliminary quick matching on the first navigation text and the menu nodes in the first menu node set, the range of the intention recognition of the subsequent menu nodes is greatly reduced, and when the intention recognition of the menu nodes is carried out, only the candidate menu determined by the preliminary matching is considered, so that the calculation complexity and the time consumption are greatly reduced, the navigation efficiency is improved, and the accuracy of the menu navigation is also improved.
Optionally, the apparatus further includes:
A fourth unit, configured to obtain historical interaction information of the first navigation text;
The third unit 603 may specifically be configured to:
And carrying out menu node intention recognition on the first navigation text according to node information corresponding to each candidate menu node and the historical interaction information, and determining a target menu node corresponding to the first navigation text in each candidate menu node.
Optionally, the third unit 603 may specifically be configured to:
Generating a task instruction according to node information corresponding to each candidate menu node, the historical interaction information and the first navigation text, wherein the task instruction is used for indicating an object receiving the task instruction to identify the menu node intention of the first navigation text according to the node information corresponding to each candidate menu node and the historical interaction information, and determining a target menu node corresponding to the first navigation text in each candidate menu node;
And inputting the task instruction into a pre-trained large language model, executing the task instruction by the pre-trained large language model, and determining a target menu node corresponding to the first navigation text from all candidate menu nodes.
Alternatively, the second unit 602 may specifically be configured to:
matching the first navigation text with node information of each menu node in a first menu node set, and determining the matching degree between the first navigation text and the node information of each menu node in the first menu node set;
and determining a preset number of candidate menu nodes in the first menu node set according to the matching degree between the first navigation text and the node information of each menu node in the first menu node set.
Optionally, the apparatus further includes:
a fifth unit, configured to generate, when a target menu node corresponding to the first navigation text is not determined in each candidate menu node, a prompt message, where the prompt message is used to prompt a user to input supplementary navigation information;
and/or the number of the groups of groups,
And a sixth unit, configured to determine a target navigation path according to the target menu node, where the target navigation path includes a navigation path from the current menu node to the target menu node.
Optionally, the matching includes keyword matching and/or semantic similarity matching, and the node information includes node name and/or node description information.
Optionally, the node information further includes entity information associated with the menu node, and/or navigation text examples corresponding to the menu node, where the entity information includes at least one of an entity name, an entity alias, and entity description information.
The menu navigation device provided in this embodiment belongs to the same application concept as the menu navigation method provided in the above embodiment of the present application, and may execute the menu navigation method provided in any of the above embodiments of the present application, and has a function module and beneficial effects corresponding to executing the menu navigation method. Technical details not described in detail in this embodiment may be referred to the specific processing content of the menu navigation method provided in the foregoing embodiment of the present application, and will not be described herein.
The functions performed by the above first unit 601, second unit 602, and third unit 603 may be implemented by the same or different processors, respectively, and embodiments of the present application are not limited.
It will be appreciated that the elements of the above apparatus may be implemented in the form of processor-invoked software. For example, the device includes a processor, where the processor is connected to a memory, and the memory stores instructions, and the processor invokes the instructions stored in the memory to implement any of the methods above or to implement functions of each unit of the device, where the processor may be a general-purpose processor, such as a CPU or a microprocessor, and the memory may be a memory within the device or a memory outside the device. Or the units in the device may be implemented in the form of hardware circuits, where the functions of some or all of the units may be implemented by designing a hardware circuit, where the hardware circuit may be understood as one or more processors, for example, in one implementation, the hardware circuit is an ASIC, where the functions of some or all of the units are implemented by designing a logic relationship between elements in the circuit, and in another implementation, the hardware circuit may be implemented by a PLD, for example, an FPGA, and may include a large number of logic gates, where the connection relationship between the logic gates is configured by a configuration file, so as to implement the functions of some or all of the units. All units of the above device may be realized in the form of processor calling software, or in the form of hardware circuits, or in part in the form of processor calling software, and in the rest in the form of hardware circuits.
In an embodiment of the present application, the processor is a circuit with signal processing capability, in one implementation, the processor may be a circuit with instruction reading and running capability, such as a CPU, a microprocessor, a GPU, or a DSP, etc., and in another implementation, the processor may implement a certain function through a logic relationship of a hardware circuit, where the logic relationship of the hardware circuit is fixed or reconfigurable, for example, the processor is a hardware circuit implemented by an ASIC or a PLD, such as an FPGA, etc. In the reconfigurable hardware circuit, the processor loads the configuration document, and the process of implementing the configuration of the hardware circuit may be understood as a process of loading instructions by the processor to implement the functions of some or all of the above units. Furthermore, a hardware circuit designed for artificial intelligence may be provided, which may be understood as an ASIC, such as NPU, TPU, DPU, etc.
It will be seen that each of the units in the above apparatus may be one or more processors (or processing circuits) configured to implement the above methods, e.g., CPU, GPU, NPU, TPU, DPU, a microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.
Furthermore, the units in the above apparatus may be integrated together in whole or in part, or may be implemented independently. In one implementation, these units are integrated together and implemented in the form of an SOC. The SOC may include at least one processor for implementing any of the methods above or for implementing the functions of the units of the apparatus, where the at least one processor may be of different types, including, for example, a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, and the like.
The embodiment of the application also provides a control device which comprises a processor and an interface circuit, wherein the processor in the control device is connected with the instruction input assembly through the interface circuit of the control device.
The instruction acquisition module 110 may be a voice input component or a text input component. The voice input component may be any functional component capable of supporting the user to input voice, for example, a microphone, a pickup, etc., and the specific voice acquisition and voice conversion processing process may be referred to as implementation process of the conventional technology. The text input component may be any functional component capable of supporting the user to input text, for example, may be a touch screen, a keyboard lamp, and a specific text acquisition processing procedure may be referred to as a conventional implementation procedure.
The instruction input component specifically refers to a functional component capable of sensing user instruction input operation, and can be a voice input component or a text input component. The voice input component can be any functional component capable of supporting the user to input voice, such as a microphone, a sound pickup and the like, and the text input component can be any functional component capable of supporting the user to input text, such as a touch screen, a keyboard lamp and the like.
The interface circuit may be any interface circuit capable of implementing a data communication function, for example, a USB interface circuit, a Type-C interface circuit, a serial interface circuit, a PCIE circuit, or the like.
The processor in the control device is also a circuit with signal processing capability, which performs menu navigation according to the navigation voice or the navigation text input by the instruction input component by executing any one of the menu navigation methods described in the above embodiments. The specific implementation manner of the processor may be referred to above, and embodiments of the present application are not limited strictly.
When the control device is applied to the intelligent equipment, the instruction input component of the control device can be the voice input component or the text input component of the intelligent equipment, meanwhile, the processor of the control device can be a CPU or a GPU and the like of the intelligent equipment, and the interface circuit of the control device can be an interface circuit between the instruction input component of the intelligent equipment and the processor of the CPU or the GPU and the like.
Exemplary electronic device
Another embodiment of the present application also proposes an electronic device, as shown in fig. 7, including:
a memory 200 and a processor 210;
wherein the memory 200 is connected to the processor 210, and is used for storing a program;
The processor 210 is configured to implement the menu navigation method disclosed in any one of the above embodiments by running the program stored in the memory 200.
In particular, the electronic device may further include a bus, a communication interface 220, an input device 230, and an output device 240.
The processor 210, the memory 200, the communication interface 220, the input device 230, and the output device 240 are interconnected by a bus. Wherein:
a bus may comprise a path that communicates information between components of a computer system.
Processor 210 may be a general-purpose processor, such as a general-purpose Central Processing Unit (CPU), microprocessor, etc., or may be an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs in accordance with aspects of the present invention. But may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
Processor 210 may include a main processor, and may also include a baseband chip, modem, and the like.
The memory 200 stores programs for implementing the technical scheme of the present invention, and may also store an operating system and other key services. In particular, the program may include program code including computer-operating instructions. More specifically, memory 200 may include read-only memory (ROM), other types of static storage devices that may store static information and instructions, random access memory (random access memory, RAM), other types of dynamic storage devices that may store information and instructions, disk storage, flash, and the like.
The input device 230 may include means for receiving data and information entered by a user, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor, among others.
Output device 240 may include means, such as a display screen, printer, speakers, etc., that allow information to be output to a user.
The communication interface 220 may include devices using any transceiver or the like for communicating with other devices or communication networks, such as ethernet, radio Access Network (RAN), wireless Local Area Network (WLAN), etc.
The processor 210 executes the program stored in the memory 200 and invokes other devices that may be used to implement the steps of any of the menu navigation methods provided by the above-described embodiments of the present application.
The embodiment of the application also provides a chip which comprises a processor and a data interface, wherein the processor reads and runs a program stored in a memory through the data interface so as to execute the menu navigation method introduced by any embodiment, and the specific processing process and the beneficial effects thereof can be introduced by referring to the embodiment of the menu navigation method.
Exemplary computer program product and storage Medium
In addition to the methods and apparatus described above, embodiments of the application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in a menu navigation method according to various embodiments of the application described in any of the embodiments of the specification.
The computer program product may write program code for performing operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, an embodiment of the present application may also be a storage medium having stored thereon a computer program that is executed by a processor to perform the steps in the menu navigation method according to various embodiments of the present application described in any of the above-described embodiments of the present specification, and specifically may implement the steps of:
step S201, acquiring a first navigation text;
Step S202, matching the first navigation text with node information of each menu node in a first menu node set, and determining a plurality of candidate menu nodes in the first menu node set according to a matching result;
and step 203, carrying out menu node intention recognition on the first navigation text according to node information corresponding to each candidate menu node, and determining a target menu node corresponding to the first navigation text in each candidate menu node.
For the foregoing method embodiments, for simplicity of explanation, the methodologies are shown as a series of acts, but one of ordinary skill in the art will appreciate that the present application is not limited by the order of acts, as some steps may, in accordance with the present application, occur in other orders or concurrently. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.
It should be noted that, in the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described as different from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other. For the apparatus class embodiments, the description is relatively simple as it is substantially similar to the method embodiments, and reference is made to the description of the method embodiments for relevant points.
The steps in the method of each embodiment of the application can be sequentially adjusted, combined and deleted according to actual needs, and the technical features described in each embodiment can be replaced or combined.
The modules and the submodules in the device and the terminal of the embodiments of the application can be combined, divided and deleted according to actual needs.
In the embodiments provided in the present application, it should be understood that the disclosed terminal, apparatus and method may be implemented in other manners. For example, the above-described terminal embodiments are merely illustrative, and for example, the division of modules or sub-modules is merely a logical function division, and there may be other manners of division in actual implementation, for example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.
The modules or sub-modules illustrated as separate components may or may not be physically separate, and components that are modules or sub-modules may or may not be physical modules or sub-modules, i.e., may be located in one place, or may be distributed over multiple network modules or sub-modules. Some or all of the modules or sub-modules may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional module or sub-module in the embodiments of the present application may be integrated in one processing module, or each module or sub-module may exist alone physically, or two or more modules or sub-modules may be integrated in one module. The integrated modules or sub-modules may be implemented in hardware or in software functional modules or sub-modules.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software unit executed by a processor, or in a combination of the two. The software elements may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410941077.2A CN118468890B (en) | 2024-07-15 | 2024-07-15 | Menu navigation method, device, equipment, storage medium and product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410941077.2A CN118468890B (en) | 2024-07-15 | 2024-07-15 | Menu navigation method, device, equipment, storage medium and product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118468890A CN118468890A (en) | 2024-08-09 |
| CN118468890B true CN118468890B (en) | 2024-12-06 |
Family
ID=92152590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410941077.2A Active CN118468890B (en) | 2024-07-15 | 2024-07-15 | Menu navigation method, device, equipment, storage medium and product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118468890B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111290677A (en) * | 2018-12-07 | 2020-06-16 | 中电长城(长沙)信息技术有限公司 | Self-service equipment navigation method and navigation system thereof |
| CN117059095A (en) * | 2023-07-21 | 2023-11-14 | 广州市睿翔通信科技有限公司 | IVR-based service providing method and device, computer equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6025785B2 (en) * | 2013-07-08 | 2016-11-16 | インタラクションズ リミテッド ライアビリティ カンパニー | Automatic speech recognition proxy system for natural language understanding |
| US10659403B2 (en) * | 2015-03-25 | 2020-05-19 | Pypestream, Inc. | Systems and methods for navigating nodes in channel based chatbots using natural language understanding |
| CN109410939B (en) * | 2018-11-29 | 2022-03-08 | 中国人民解放军91977部队 | Universal data maintenance method based on voice instruction set |
| CN111800551A (en) * | 2019-04-09 | 2020-10-20 | 中国移动通信集团山东有限公司 | Method, device, electronic device and storage medium for generating voice navigation menu |
-
2024
- 2024-07-15 CN CN202410941077.2A patent/CN118468890B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111290677A (en) * | 2018-12-07 | 2020-06-16 | 中电长城(长沙)信息技术有限公司 | Self-service equipment navigation method and navigation system thereof |
| CN117059095A (en) * | 2023-07-21 | 2023-11-14 | 广州市睿翔通信科技有限公司 | IVR-based service providing method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118468890A (en) | 2024-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230376696A1 (en) | Techniques for out-of-domain (ood) detection | |
| US11868727B2 (en) | Context tag integration with named entity recognition models | |
| US20240013780A1 (en) | Entity level data augmentation in chatbots for robust named entity recognition | |
| US12099816B2 (en) | Multi-factor modelling for natural language processing | |
| US10831811B2 (en) | Resolution of ambiguous and implicit references using contextual information | |
| US11928430B2 (en) | Detecting unrelated utterances in a chatbot system | |
| CN114424185A (en) | Stop word data augmentation for natural language processing | |
| US12210842B2 (en) | Distance-based logit value for natural language processing | |
| US11972220B2 (en) | Enhanced logits for natural language processing | |
| US11777874B1 (en) | Artificial intelligence conversation engine | |
| US20230115321A1 (en) | Fine-tuning multi-head network from a single transformer layer of pre-trained language model | |
| CN118235143A (en) | Path deactivation for natural language processing | |
| CN118468890B (en) | Menu navigation method, device, equipment, storage medium and product | |
| US20230325599A1 (en) | Training data augmentation using gazetteers and perturbations to facilitate training named entity recognition models | |
| US20240062108A1 (en) | Techniques for training and deploying a named entity recognition model | |
| US12210830B2 (en) | System and techniques for handling long text for pre-trained language models | |
| CN117059095A (en) | IVR-based service providing method and device, computer equipment and storage medium | |
| US20240062112A1 (en) | Adaptive training data augmentation to facilitate training named entity recognition models | |
| CN119768794A (en) | Adaptive training data augmentation to facilitate training of named entity recognition models | |
| CN114969276A (en) | Query processing method, device, equipment and storage medium | |
| WO2023091436A1 (en) | System and techniques for handling long text for pre-trained language models | |
| WO2024044491A1 (en) | Adaptive training data augmentation to facilitate training named entity recognition models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |