Function navigation method and device, equipment, storage medium and program product

Abstract

The invention relates to a function navigation method and device, equipment, a storage medium and a program product, and the method relates to the technical field of Internet of Things, and the method comprises the following steps: responding to a function navigation request of a target function triggered by a user in a target application program, obtaining function query information of the target function, and generating a navigation strategy of the target function based on the function query information and the scene definition information of each function of the target application program, and then displaying the navigation strategy of the target function to indicate a user to search the target function according to the navigation strategy. According to the method, the efficiency of searching the function service in the target application program is improved.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a function navigation method, device, equipment, storage medium and program product. Background Art

[0002] With the continuous development of banking business and the improvement of overall capabilities, more and more functional services are integrated into mobile banking. In the related art, when using a certain function of mobile banking, users are usually required to manually search for the function in mobile banking.

[0003] However, since mobile banking has many functional services, the method of searching for functional services is inefficient. Summary of the invention

[0004] Based on this, it is necessary to provide a function navigation method, device, equipment, storage medium and program product to address the above technical problems, which can improve the efficiency of function service search in mobile banking.

[0005] In a first aspect, an embodiment of the present application provides a function navigation method, including:

[0006] In response to a function navigation request of a target function triggered by a user in a target application, obtaining function query information of the target function;

[0007] Generate a navigation strategy for the target function based on the function query information and the scenario definition information of each function of the target application;

[0008] The navigation strategy of the target function is displayed to instruct the user to find the target function according to the navigation strategy.

[0009] In one embodiment, obtaining function query information of a target function includes:

[0010] Verify the legitimacy of the function navigation request of the target function;

[0011] If the legitimacy verification of the function navigation request passes, the function query information is obtained from the function navigation request of the target function;

[0012] If the function navigation request fails the legitimacy verification, the function navigation request is determined to be invalid.

[0013] In one embodiment, the legitimacy of the function navigation request of the target function is verified, including:

[0014] Verify the user's identity information based on the user's identity identifier in the function navigation request;

[0015] If the user's identity information is verified, the validity of the user's function navigation request is verified;

[0016] When the user's identity information verification fails, it is determined that the legitimacy verification of the function navigation request of the target function fails.

[0017] In one embodiment, the validity of the user's function navigation request is verified, including:

[0018] Verify the validity of the request format and parameters of the function navigation request;

[0019] If the request format and parameters in the function navigation request are correct, it is determined that the legitimacy verification of the function navigation request has passed;

[0020] If there are errors in the request format and parameters in the function navigation request, it is determined that the function navigation request legality verification fails.

[0021] In one embodiment, the scenario definition information includes a semantic mapping relationship and context interaction information; based on the function query information and the scenario definition information of each function of the target application, a navigation strategy for the target function is generated, including:

[0022] Based on the semantic mapping relationship, the standard function query information of the target function is determined by semantically analyzing the function query information;

[0023] The standard function query information is parsed through contextual interaction information to determine the navigation strategy of the target function.

[0024] In one embodiment, the context interaction information includes context logic information and reply rules; parsing the standard function query information through the context interaction information to determine the navigation strategy of the target function includes:

[0025] Analyze the standard function query information according to the context logic information to determine the module scheduling information; the module scheduling information includes the scheduling order of at least one processing module;

[0026] Executing each processing module in sequence according to the scheduling order of at least one processing module to obtain an execution result of each processing module;

[0027] According to the response rules, the execution results of each processing module are integrated to obtain the navigation strategy of the target function.

[0028] In one embodiment, the method further comprises:

[0029] According to the navigation strategy, the user is instructed to find the target function through voice navigation.

[0030] In a second aspect, the present application further provides a functional navigation device, the device comprising:

[0031] an acquisition module, configured to acquire function query information of a target function in response to a function navigation request of a target function triggered by a user in a target application;

[0032] A generation module, for generating a navigation strategy for a target function based on the function query information and the scenario definition information of each function of the target application;

[0033] The search module is used to display the navigation strategy of the target function to instruct the user to search for the target function according to the navigation strategy.

[0034] In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method provided in any embodiment of the first aspect when executing the computer program.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in any embodiment of the first aspect above.

[0036] In a fifth aspect, an embodiment of the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method provided in any embodiment of the first aspect above.

[0037] The above-mentioned function navigation method, apparatus, device, storage medium and program product, in response to a function navigation request of a target function triggered by a user in a target application, obtains function query information of the target function, and generates a navigation strategy of the target function based on the function query information and the scenario definition information of each function of the target application, and then displays the navigation strategy of the target function to instruct the user to find the target function according to the navigation strategy. In this method, after receiving the function navigation request of the target function of the user, the computer device obtains the function query information of the target function, and then determines the navigation strategy of the target function based on the pre-defined scenario definition information of each function of the target application. The user can directly find the target function in the target application through the navigation strategy, thereby improving the efficiency of finding function services in the target application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are 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 creative work.

[0039] Figure 1is an internal structure diagram of a computer device in one embodiment;

[0040] Figure 2 is a flowchart of a function navigation method in one embodiment;

[0041] Figure 3 is a flowchart of a function navigation method in another embodiment;

[0042] Figure 4 is a flowchart of a function navigation method in another embodiment;

[0043] Figure 5 is a flowchart of a function navigation method in another embodiment;

[0044] Figure 6 is a flowchart of a function navigation method in another embodiment;

[0045] Figure 7 is a flowchart of a function navigation method in another embodiment;

[0046] Figure 8 is a schematic diagram of the structure of a function navigation system in one embodiment;

[0047] Fig. 9 is a flowchart of a function navigation method in another embodiment;

[0048] Fig.10 is a flowchart of a function navigation method in another embodiment;

[0049] Fig.11 FIG. 4 is a structural block diagram of a functional navigation device in an embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] The function navigation method provided in the embodiment of the present application is applied to Figure 1 The computer device in FIG. 1 is used as an example to illustrate. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 1As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store function navigation data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a function navigation method is implemented.

[0052] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a partial structure related to the embodiment of the present application, and does not constitute a limitation on the computer device to which the embodiment of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0053] In an exemplary embodiment, Figure 2 As shown, a function navigation method is provided, which is applied to Figure 1 The computer device in the example is used to illustrate, including the following S201 to S203. Among them:

[0054] S201 , in response to a function navigation request of a target function triggered by a user in a target application, obtaining function query information of the target function.

[0055] Among them, the target application can be the application to be accessed in the user's terminal device. For example, taking the terminal device as a mobile phone and the target application as mobile banking, when the user needs to access the functions in the mobile banking, the user can open the mobile banking on the mobile phone and enter the function to be navigated on the mobile banking. The mobile banking generates a function navigation request for the function based on the function to be navigated entered by the user, wherein the target function is the function to be navigated by the user.

[0056] The method for the user to trigger a function navigation request for the target function in the target application can be: the user enters or selects the target function in the target application in the user's terminal device, the target application generates a function navigation request for the target function based on the user input or selection of the target function, and sends the navigation request to the computer device.

[0057] After receiving the function navigation request of the target function triggered by the user in the target application, the computer device obtains the function query information of the target function; wherein the function query information of the target function may include the name, attributes and other information of the target function.

[0058] The function navigation request of the target function may include function query information of the target function, so the computer device may directly obtain the function query information of the target function from the function navigation request of the target function.

[0059] Optionally, the function navigation request of the target function may also include identification information of the target function, and the identification information may uniquely identify the target function. The correspondence between the identification information and the function query information is stored in the computer device. Therefore, the computer device may obtain the identification information of the target function from the function navigation request of the target function, and obtain the function query information corresponding to the identification information of the target function according to the correspondence, and determine the function query information corresponding to the identification information of the target function in the correspondence as the function query information of the target function.

[0060] S202: Generate a navigation strategy for the target function based on the function query information and the scenario definition information of each function of the target application.

[0061] Among them, the scenario definition information can be the definition of each scenario for each function in the pre-defined target application, which can include a text description of the business scenario in the target application, key attributes of the business scenario, contextual dialogue logic relationships, reply information rules, and processing module selection.

[0062] Therefore, a navigation strategy for the target function can be generated based on a preset navigation model. For example, function query information and scenario definition information of each function of the target application are input into the navigation model. Through the analysis of the function query information and the scenario definition information of each function by the navigation model, the navigation model outputs the navigation strategy for the target function.

[0063] The navigation strategy may include steps on how to find the target function in the target application. For example, the navigation strategy includes the current page, page A, page B, and target function page of the target application.

[0064] S203, displaying the navigation strategy of the target function to instruct the user to search for the target function according to the navigation strategy.

[0065] The computer device sends the obtained navigation strategy of the target function to the target application, and controls the navigation strategy of the target function to be displayed in the target application, so as to instruct the user to find the target function according to the navigation strategy.

[0066] For example, the target strategy includes the current page of the target application, page A, page B, and the target function page. Therefore, the user can sequentially go from the current page of the target application to page A, from page A to page B, and from page B to the target function page, and then find the target function in the target function page.

[0067] The navigation strategy for the target function may be displayed in a manner of directly displaying all the navigation strategies in the target application, and the user may search for the target function in sequence according to all the displayed navigation strategies.

[0068] Optionally, the navigation strategy for the target function may be displayed in sequence in the target application, that is, the user's next operation in the navigation strategy is displayed in sequence, and after the user completes the operation, the current next operation continues to be displayed until the target function is found.

[0069] In the function navigation method provided by the embodiment of the present application, in response to a function navigation request of a target function triggered by a user in a target application, function query information of the target function is obtained, and a navigation strategy of the target function is generated based on the function query information and the scenario definition information of each function of the target application, and then the navigation strategy of the target function is displayed to instruct the user to find the target function according to the navigation strategy. In this method, after receiving the function navigation request of the target function of the user, the computer device obtains the function query information of the target function, and then determines the navigation strategy of the target function based on the pre-defined scenario definition information of each function of the target application. The user can directly find the target function in the target application through the navigation strategy, thereby improving the efficiency of finding functional services in the target application.

[0070] In one embodiment, Figure 3 As shown, obtaining function query information of the target function includes the following steps:

[0071] S301, verify the legitimacy of the function navigation request of the target function.

[0072] The legitimacy verification of the function navigation request of the target function may include identity verification, authority verification, data verification, security verification, etc.

[0073] Among them, identity authentication includes that the requester of the function navigation request is a legitimate user or an authorized user, and an identity authentication mechanism can be used, for example, to verify the identity of the user through information such as a user name and password.

[0074] Permission verification includes confirming whether the user has the authority to execute the navigation request, for example, ensuring whether the user is a member. If the user is a member, determining whether the legitimacy verification of the function navigation request of the target function has passed.

[0075] Data verification includes verifying the data in the function navigation request to ensure that it conforms to the expected format and range, for example, verifying whether the data format in the function navigation request is the preset format. If the data format in the function navigation request is the preset format, it is determined that the function navigation request of the target function is legal, and the legality verification of the function navigation request of the target function passes.

[0076] The security verification includes confirming whether the function navigation request is sent through a secure communication protocol. If the communication protocol used to send the function navigation request is in a preset list of protocols, it is determined that the legitimacy verification of the function navigation request for the target function has passed.

[0077] It should be noted that the legitimacy of the function navigation request of the target function can be verified through one or more of identity verification, permission verification, data verification and security verification. If multiple verification methods are passed, it is determined that the legitimacy of the function navigation request of the target function is passed. If there is one verification method that fails, it is determined that the legitimacy of the function navigation request of the target function is failed.

[0078] S302: If the legitimacy verification of the function navigation request passes, obtaining function query information from the function navigation request of the target function.

[0079] If the legitimacy verification of the function navigation request passes, the function query information is obtained from the function navigation request of the target function.

[0080] There is function query information in the function navigation request of the target function, and the function query information can be directly obtained from the function navigation request of the target function.

[0081] The function query information may include the name of the function to be navigated to, the name of the current page in the target application, the name of the current function, etc.

[0082] S303: If the legitimacy verification of the function navigation request fails, it is determined that the function navigation request is invalid.

[0083] Among them, the purpose of legitimacy verification is to ensure that the user has the legal authority and identity required to execute the functional navigation request, and that the requested data conforms to the expected format and scope, etc.

[0084] If the legitimacy verification of the function navigation request fails, it can be determined that the function navigation request is invalid. Further, the computer device can generate an invalid request prompt and send the invalid request prompt to the target application to instruct the user to correct the legitimacy of the function navigation request and resend the function navigation request.

[0085] In the function navigation method provided in the embodiment of the present application, the function navigation request of the target function is subjected to a legitimacy verification. If the legitimacy verification of the function navigation request is passed, the function query information is obtained from the function navigation request of the target function. If the legitimacy verification of the function navigation request is not passed, the function navigation request is determined to be invalid. In this method, by conducting a legitimacy verification on the function navigation request of the target function, the function navigation request is executed only when the legitimacy verification of the function navigation request of the target function is passed, thereby improving the security of business processing.

[0086] In one embodiment, Figure 4 As shown, the legitimacy of the function navigation request of the target function is verified, including the following steps:

[0087] S401, verifying the user's identity information according to the user's identity identifier in the function navigation request.

[0088] The function navigation request includes the user's identity, wherein the identity is unique and can uniquely identify the user.

[0089] Therefore, the computer device can search the database for an identity identifier that is identical to the user's identity identifier. If an identity identifier that is identical to the user's identity identifier exists in the database, it means that the user has the function navigation request permission, and it is determined that the user's identity information verification has passed. If an identity identifier that is identical to the user's identity identifier does not exist in the database, it is determined that the user's identity information verification has failed.

[0090] S402: When the user's identity information is verified, the validity of the user's function navigation request is verified.

[0091] When the user's identity information is verified, the user's function navigation request may be verified for validity. In one embodiment, Figure 5 As shown, the validity verification of the user's function navigation request includes the following steps:

[0092] S501, verify the validity of the request format and parameters of the function navigation request.

[0093] The function navigation request may be parsed through a preset parsing protocol to determine the request format and parameters of the function navigation request, wherein the request format may include a Get or Post request method, and the parameter may be function query information.

[0094] Detect whether the request format of the function navigation request is a preset request format, and detect whether the parameters in the function navigation request are within a preset detection range. If the request format of the function navigation request is the preset request format, determine that the request format validity verification of the function navigation request has passed, that is, the request format of the function navigation request is correct; if the request format of the function navigation request is not the preset request format, determine that the request format of the function navigation request is wrong; if the parameters in the function navigation request are within the preset detection range, determine that the parameter validity verification of the function navigation request has passed, that is, the parameters in the function navigation request are correct; if the parameters in the function navigation request are not within the preset detection range, determine that the parameters in the function navigation request are wrong.

[0095] S502: If the request format and parameters in the function navigation request are correct, it is determined that the legitimacy verification of the function navigation request has passed.

[0096] Because the user's identity information has been verified before detecting the request format and parameters in the function navigation request, the request format and parameters in the function navigation request will be verified only when the user's identity information verification is passed. If all the parameters of the request format in the function navigation request are correct, it means that the user's identity information, the request format and parameters of the function navigation request are all verified, and it is determined that the legitimacy of the function navigation request has passed the verification.

[0097] S503: If there are errors in the request format and parameters in the function navigation request, it is determined that the legitimacy verification of the function navigation request fails.

[0098] If there are errors in the request format and parameters in the function navigation request, it means that the request format in the function navigation request is wrong, or the parameters in the function navigation request are wrong, or both the request format and parameters in the function navigation request are wrong, then it is determined that the function navigation request legality verification fails.

[0099] S403: When the user's identity information verification fails, determining that the function navigation request of the target function fails the legitimacy verification.

[0100] If the user's identity information verification fails, it means that there is a problem with the user's identity information, and then it is determined that the legitimacy verification of the function navigation request of the target function fails.

[0101] In the function navigation method provided in the embodiment of the present application, the user's identity information is verified according to the user's identity identifier in the function navigation request; when the user's identity information verification passes, the validity of the user's function navigation request is verified; when the user's identity information verification fails, it is determined that the legitimacy verification of the function navigation request of the target function fails. In this method, the legitimacy verification of the function navigation request includes verifying the user's identity information, the request format and parameters in the function navigation request. Only when the user's identity information verification passes, the request format and parameters of the function navigation request are further verified, which reduces the need to verify the request format and parameters of the function navigation request in the case of a request with incorrect user identity information, thereby improving the efficiency of the legitimacy verification of the function navigation request.

[0102] In one embodiment, Figure 6 As shown, the scenario definition information includes semantic mapping relationship and context interaction information; based on the function query information and the scenario definition information of each function of the target application, a navigation strategy of the target function is generated, including the following steps:

[0103] S601, determining standard function query information of a target function by performing semantic analysis on the function query information based on the semantic mapping relationship.

[0104] Among them, the function query information is the information of the query function input by the user. However, there may be a problem that the semantics of the function query information is not standardized. Therefore, the function query information can be semantically analyzed to rewrite the function query information in a semantically standardized manner to obtain a business professional expression in the target application, that is, standard function query information.

[0105] Specifically, semantic analysis can be performed on the function query information according to the semantic mapping relationship to obtain standard function query information of the target function, wherein the semantic mapping relationship may include a semantic mapping relationship between a professional expression of a business function in a target application and the function query information of a user.

[0106] Among them, the function query information may include the query words of the functions that the user needs to navigate. Optionally, the process of constructing the semantic mapping relationship includes: driven by objective data, based on the user's search history log, using natural language processing and text mining technology, statistically analyzing the word distribution of the query words in the search history log, mining the semantic associations between the words, and thus constructing the semantic mapping relationship between the professional expression of the business function in the target application and the query words, so as to guide the rewriting of the query words. In this way, the obtained new query (standard function query information) can not only more objectively and reliably reflect the user's needs, but also its expression is more in line with the expression habits of the corresponding field of the target application.

[0107] Specifically, the Pointwise Mutual Information (PMI) model can be used to statistically evaluate the co-occurrence of words in the same context, explore the mapping relationship between related words, and construct a demand-related word list.

[0108] Build a Word2vec language model to model synonymous relationships; use PMI to evaluate the co-occurrence of words and confirm the association between words (demand association word list), which can more accurately and comprehensively reflect the relationship between words.

[0109] Then, keyword extraction based on part-of-speech rules and TextRank keyword recognition integrates human experience with general technology, further improving the accuracy of keyword extraction and laying the foundation for subsequent operations. Based on basic word segmentation, through the mutual information model, the co-occurrence of adjacent words is counted, and large-grained words are mined to complete the expansion of professional terms in the target application, thereby obtaining semantic mapping relationships and guiding the online search system to perform more accurate word segmentation, entity recognition and other operations.

[0110] S602: parse the standard function query information through the context interaction information to determine the navigation strategy of the target function.

[0111] Based on the standard function query information obtained above, the standard function query information is parsed through predefined context interaction information to obtain a navigation strategy for the target function.

[0112] In one embodiment, Figure 7 As shown, the context interaction information includes context logic information and reply rules; parsing the standard function query information through the context interaction information to determine the navigation strategy of the target function includes the following steps:

[0113] S701, analyzing standard function query information according to context logic information to determine module scheduling information; the module scheduling information includes a scheduling order of at least one processing module.

[0114] Among them, the context logic information may include context logic management rules and related processing logic. Through the context logic management rules and related processing logic, the standard function query information is parsed to generate module scheduling information, that is, the system coordinates the scheduling plan of each processing module, including the scheduling order of each processing module, etc.

[0115] Specifically, the contextual logic information may be a business logic control model, the standard function query information is input into the business logic control model, the standard function query information is analyzed by the business logic control model, and the business logic control model outputs module scheduling information.

[0116] S702, executing each processing module in sequence according to the scheduling order of at least one processing module to obtain the execution result of each processing module.

[0117] Based on the module scheduling information obtained above, each processing module is scheduled in turn according to the scheduling order of each processing module in the module scheduling information to obtain the execution result of each processing module.

[0118] S703, integrating the execution results of the processing modules according to the response rules to obtain the navigation strategy of the target function.

[0119] Then, according to the preset response rules, the execution results of each processing module are integrated to generate the final response content, that is, the navigation strategy of the target function.

[0120] Optionally, the navigation strategy of the target function may be returned to the target application of the user's terminal device.

[0121] In the function navigation method provided by the embodiment of the present application, the context interaction information includes context logic information and reply rules. The standard function query information is analyzed according to the context logic information to determine the module scheduling information; wherein the module scheduling information includes the scheduling order of at least one processing module; then, according to the scheduling order of at least one processing module, each processing module is executed in sequence to obtain the execution result of each processing module, and finally, according to the reply rules, the execution results of each processing module are integrated to obtain the navigation strategy of the target function. In this method, the module scheduling information corresponding to the standard function query information is directly generated through the context interaction information, and then each processing module is scheduled, and the processing results of each processing module are integrated according to the preset reply rules to obtain the navigation strategy of the target function, thereby improving the efficiency of subsequent search for the target function according to the navigation strategy.

[0122] In the function navigation method provided in the embodiment of the present application, based on the semantic mapping relationship, the standard function query information of the target function is determined by semantically analyzing the function query information, and the standard function query information is parsed through the context interaction information to determine the navigation strategy of the target function. In this method, by semantically analyzing the function query information, the business professional terms in the target application are obtained, which improves the accuracy of matching user needs, thereby improving the efficiency of navigating the target function; and the standard function query information is parsed with the context interaction information to improve the accuracy of the navigation strategy of the target function.

[0123] In one embodiment, the embodiment includes: according to the navigation strategy, instructing the user to find the target function by voice navigation.

[0124] The computer device generates voice information corresponding to the navigation strategy according to the navigation strategy and the voice generation module, and then instructs the user to find the target function in the target application through the voice information.

[0125] In the function navigation method provided in the embodiment of the present application, according to the navigation strategy, the user is instructed to find the target function by voice navigation. In this method, the user is guided to find the target function by voice navigation, which improves the speed and convenience of finding the target function.

[0126] In one embodiment, Figure 8 As shown, a functional navigation system is also provided in an embodiment of the present application, the functional navigation system includes an access layer and a language navigation service device, the language navigation service device includes an operation console, a service request processing module, wherein the core service processing module includes a business logic control unit and a natural language understanding unit, wherein the request distribution unit has the function of forwarding information, forwarding the data of the access layer to the business logic control unit through the first request distribution unit, and sending the data of the business logic control unit to the natural language understanding unit through the second request distribution unit. The business logic control unit and the natural language understanding unit are both connected to a database, wherein the database includes MongoDB and redis, etc.

[0127] The access layer is responsible for processing the input and output messages of the interface (Application Programming Interface, API) requests between programs. It includes listening to and accepting API requests from the user's target application, parsing API requests, extracting information from API requests, clustering API requests based on sessionid, encapsulating the execution results of each processing module, generating navigation strategies, and sending navigation strategies to user terminals. The access layer mainly interacts with the service request processing module. Among them, API requests can include function navigation requests.

[0128] The operation console is used for service application users to register and log in to the platform. Service application users complete operations such as permission application, service customization, instantiated service, API release tasks, etc. based on the operation console. For service customization, users can upload and download data, preset and change parameters, save scenarios, verify and publish results, etc. through the visual interface of the operation console. Service application users can be business personnel, that is, the party who proposes the demand. Among them, the definition operations of the scenario mainly include: text description of the target business scenario, formulation of key attributes of specific business scenarios, construction of context dialogue logic relationships, construction of reply information rules, and selection of Pipeline processing modules. Among them, all the above operation processes of the operation console are completed by interacting with the service request processing module.

[0129] The service request processing module is responsible for responding to all processing requests sent by the front-end (user) and the back-end (service application user), analyzing the response type, and making corresponding scheduling decisions.

[0130] Among them, the response types include various operation behavior responses of the backend service application users (in addition to the above key operations, it also includes various commonly used database operation responses). And the function navigation requests of the front-end (terminal) users, mainly including semantic analysis of the function navigation requests, dispatching various related function service modules according to the analysis results, and finally integrating the information and returning it to the user.

[0131] The service request processing module includes parsing user requests and automatically locating required services based on business scenario text descriptions and preset pipeline parsing rules; maintaining user interaction session consistency, and interacting with end users to confirm information based on preset context interaction information; integrating various resources based on parsing results, and returning user request results (navigation strategy) based on response rules.

[0132] Among them, the business logic control unit, on the one hand, responds to the request of the back end (service application user), mainly including a series of operations such as creating a query session agent, adding a query target description, configuring a three-party service link interface, and defining session rules; on the other hand, it responds to the function query information of the front-end user, based on the specific service query interaction rules, the current user session, and the interaction status (context information), and decides the subsequent execution logic of the decision system; then it schedules other processing modules, integrates the execution results of each processing module, generates the final navigation strategy according to the reply rules, and returns it to the user's terminal.

[0133] Depending on the response type of the background operation, it mainly includes the setting operation of parameters related to the database and query session agent, as well as the natural language understanding unit.

[0134] Among them, docking with the database may include completing the corresponding creation, modification, query, deletion and other operations on the database according to the type of data processing request sent by the operation console. Specifically, it includes: first, creation, modification, query, and deletion operations of query target description and interaction logic rules. Optionally, during the creation process, the business logic control unit updates the database in real time on the one hand, and automatically starts the query target semantic recognition (generalization) training module on the other hand after the service application user confirms the customized query target interaction content, and updates the query target semantic recognition model in real time. Second, creation, modification, query, and deletion operations of specific scene semantic recognition models. Optionally, during the creation and modification process, the business logic control unit updates the database in real time on the one hand, and automatically starts the core training module on the other hand to generate a semantic recognition (generalization) model of the corresponding target object. Third, creation, modification, query, and deletion operations of three-party service links.

[0135] In addition, the business logic control unit also supports batch upload and download operations on the generated query target session scenarios.

[0136] Optionally, the operation of setting parameters related to the query session agent may include:

[0137] First, the selection of pipeline-related processing modules of the semantic understanding module can include word segmentation, entity recognition, text classification, semantic matching models and rules, etc. In the process of responding to the front-end (terminal user) function navigation request, the business logic control unit sends the corresponding query target session agent ID, user session and the status of the current interaction node to the natural language processing unit. The natural language processing unit sequentially loads the relevant processing modules according to the pipeline configuration rules corresponding to the query target session agent and completes the core semantic parsing task.

[0138] Second, the setting of general parameters, including querying the target session agent type (shared, private), publishing status, parameters related to background query display rules, etc.

[0139] Optionally, the processing result information of each module is integrated, and the final reply content is generated according to preset reply rules and returned to the end user.

[0140] In one embodiment, the natural language understanding unit may include a tool set related to natural language processing, including word segmentation, part-of-speech recognition, entity recognition, keyword recognition, semantic model and other processing tools. The specific process includes monitoring the request of the business logic control unit, calling the corresponding core semantic understanding processing module to complete the relevant text request target parsing according to the request type and the preset pipeline processing rules, and feeding back the results to the business logic control unit for information integration and subsequent execution logic decision.

[0141] In one embodiment, taking mobile banking as the target application, the embodiment of the present application includes: extracting the voice navigation function processing module (voice navigation service module) of the mobile banking production environment, and based on this, componentizing and packaging the voice navigation function processing module of the mobile banking production environment, integrating a web-operable interface, and making its development process configurable and automated.

[0142] Specifically, the common processing mechanism of the voice navigation function processing module in the mobile banking production environment is extracted, the development process is sorted out, and the component automation operation specification design is completed in combination with the web operation interface; based on the pipeline processing idea, the core processing tasks are disassembled and modularized, so that the voice navigation function processing module in the mobile banking production environment can be adaptively customized, improve the core problem-solving ability, and complete the pipeline processing process development at the same time; complete the design of contextual logic management rules and the formulation of related processing logic. Its purpose is to respond to terminal user requests, generate system coordination scheduling plans for various modules, and complete related module calculations and result integration based on this; the core of the text understanding module is to parse the terminal user input text demand goals and related parameter attributes, and can match user needs through semantic retrieval to adapt to the rapid construction of core understanding capabilities in different scenarios; design of reply information rules of different types (text, H5, etc.), and implementation of related processing logic.

[0143] The function navigation method provided in the embodiment of the present application is based on the traditional search architecture. From the perspective of understanding the search query terms, it uses natural language processing and text mining technology to construct a semantic mapping relationship between the professional expression of mobile banking financial services and the user search keywords, thereby rewriting the online search query terms in a standardized expression to improve the accuracy and recall rate of mobile banking search results; and, with big data as the background and based on a large amount of search history, completes the semantic relationship analysis between the professional expression of financial services and the user search keywords, and the result is more objective, scientific and reasonable; in addition, the mutual information (PMI), TextRank, Word2vec and other advanced technologies are used to model the feature words, and the method is more reliable, and this automated data analysis process improves the efficiency of data analysis and reduces the cost of scientific research.

[0144] In one embodiment, Fig. 9 As shown, this embodiment includes an interaction process between a service application user and a service request processing module, wherein the interaction process mainly includes three parts: service instantiation, service definition and service publishing.

[0145] First, the service applicant logs in to the operating console, and the operating console returns a response to the service applicant that the user has logged in successfully. After receiving the response from the operating console, the service applicant selects a service from the operating console. After the operating console returns a message to the service applicant that the operating console has been successfully selected, the service applicant creates a request for the service on the operating console, and the operating console creates the service in the business logic control unit. The business logic control unit also creates the service in the natural language understanding unit at this time. After the natural language understanding unit creates the service, it instantiates the service and provides feedback to the service applicant.

[0146] The service applicant logs in to the console based on the instantiated service and defines the service after successfully logging in to the console. Taking a service as an example, the service applicant sets parameters on the business logic control unit through the console. After the business logic control unit successfully sets the parameters, it updates the database and builds a model and updates the service in the natural language understanding unit based on the updated database. After the service is successfully updated, a specific scenario service is generated in the business logic control unit and returned to the service applicant through the console.

[0147] The service applicant verifies the effect of the generated specific scenario service. The service applicant sends an effect verification request to the business logic control unit through the operation console. The business logic control unit returns the service entry address to the service applicant through the operation console, and the service applicant performs the test according to the service entry address. The testing method includes: the service applicant inputs the test case on the operation console, the business logic unit executes the test case, generates module scheduling information, calls the corresponding processing module from the natural language understanding unit according to the module scheduling information, and returns the execution results of each processing module to the business logic control unit. The business logic control unit integrates the execution results of each processing module and returns the integrated results to the service applicant through the operation console. After the service applicant successfully tests, the service release operation is performed, and the operation console returns the release status information to the service applicant.

[0148] In one embodiment, after the service is successfully released, a function navigation request can be sent to the service request processing module through the front-end user, such as Fig.10 As shown, taking mobile banking as the target application, specifically, the user sends an API request to the access layer through mobile banking. After receiving the API request, the access layer parses the API request to obtain the user's function query information, and then sends the function query information to the business logic control unit through the diversion call service. The business logic control unit parses the function query information, generates module scheduling information, and then calls each processing module in the natural language understanding unit according to the module scheduling information. The natural language understanding module returns the execution results of each processing module to the business logic control unit, and then the business logic control unit integrates the execution results of each processing module and sends the integrated results to the access layer. The access layer encapsulates the integrated results according to the preset reply rules, obtains the navigation strategy, and returns the navigation strategy to the user.

[0149] Optionally, after receiving the user's API request, the access layer can parse the API request to confirm the user's identity information and the legitimacy of the requested service. If the legitimacy verification passes, the function query information is sent to the business logic control unit for subsequent operations. If the legitimacy verification fails, a prompt message indicating that the API request is illegal can be sent to the user.

[0150] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0151] Based on the same inventive concept, the embodiment of the present application also provides a function navigation device for implementing the function navigation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more function navigation device embodiments provided below can refer to the limitations on the function navigation method above, and will not be repeated here.

[0152] In an exemplary embodiment, Fig.11 As shown, a function navigation device 1100 is provided, comprising: an acquisition module 1101, a generation module 1102 and a search module 1103, wherein:

[0153] An acquisition module 1101 is used to acquire function query information of a target function in response to a function navigation request of a target function triggered by a user in a target application;

[0154] A generating module 1102, for generating a navigation strategy for a target function based on the function query information and the scenario definition information of each function of the target application;

[0155] The search module 1103 is used to display the navigation strategy of the target function to instruct the user to search for the target function according to the navigation strategy.

[0156] In one embodiment, the acquisition module 1101 includes:

[0157] A verification unit, used to verify the legitimacy of a function navigation request of a target function;

[0158] A first judgment unit is used to obtain function query information from the function navigation request of the target function if the legitimacy verification of the function navigation request passes;

[0159] The second judgment unit is used to determine that the function navigation request is invalid if the function navigation request fails the legitimacy verification.

[0160] In one embodiment, the verification unit includes:

[0161] A first verification subunit is used to verify the identity information of the user according to the identity identifier of the user in the function navigation request;

[0162] The second verification subunit is used to verify the validity of the user's function navigation request when the user's identity information is verified;

[0163] The first determining subunit is used to determine that the legitimacy verification of the function navigation request of the target function fails when the user's identity information verification fails.

[0164] In one embodiment, the second verification subunit includes:

[0165] A third verification subunit is used to verify the validity of the request format and parameters of the function navigation request;

[0166] A second determining subunit is used to determine that the legitimacy verification of the function navigation request has passed if the request format and parameters in the function navigation request are correct;

[0167] The third determining subunit is configured to determine that the legitimacy verification of the function navigation request fails if there are errors in the request format and parameters in the function navigation request.

[0168] In one embodiment, the scene definition information includes semantic mapping relationship and context interaction information; the generation module 1102 includes:

[0169] An analysis unit, configured to determine standard function query information of a target function by performing semantic analysis on the function query information based on a semantic mapping relationship;

[0170] The parsing unit is used to parse the standard function query information through the context interaction information and determine the navigation strategy of the target function.

[0171] In one embodiment, the context interaction information includes context logic information and reply rules; the parsing unit includes:

[0172] An analysis subunit, configured to analyze the standard function query information according to the contextual logic information and determine the module scheduling information; the module scheduling information includes a scheduling order of at least one processing module;

[0173] An execution subunit, configured to execute each processing module in sequence according to a scheduling order of at least one processing module, and obtain an execution result of each processing module;

[0174] The integration subunit is used to integrate the execution results of each processing module according to the response rules to obtain the navigation strategy of the target function.

[0175] In one embodiment, the apparatus 1100 further includes:

[0176] The instruction module is used to instruct the user to find the target function through voice navigation according to the navigation strategy.

[0177] Each module in the above functional navigation device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0178] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0179] The implementation principles and technical effects of each step implemented by the processor in the embodiment of the present application are similar to the principles of the above-mentioned function navigation method, and will not be repeated here.

[0180] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0181] The implementation principles and technical effects of the various steps implemented when the computer program in the embodiment of the present application is executed by the processor are similar to the principles of the above-mentioned function navigation method, and will not be repeated here.

[0182] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0183] The implementation principles and technical effects of the various steps implemented when the computer program in the embodiment of the present application is executed by the processor are similar to the principles of the above-mentioned function navigation method, and will not be repeated here.

[0184] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0185] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0186] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0187] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A function navigation method, characterized in that: The method comprises: In response to a function navigation request of a target function triggered by a user in a target application, acquiring function query information of the target function; generating a navigation strategy for the target function based on the function query information and the scenario definition information of each function of the target application; The navigation strategy of the target function is displayed to instruct the user to search for the target function according to the navigation strategy.

2. The method according to claim 1, characterized in that The step of obtaining the function query information of the target function includes: Verify the legitimacy of the function navigation request of the target function; If the legitimacy verification of the function navigation request passes, acquiring the function query information from the function navigation request of the target function; If the legitimacy verification of the function navigation request fails, it is determined that the function navigation request is invalid.

3. The method according to claim 2, characterized in that The legitimacy verification of the function navigation request of the target function includes: Verifying the identity information of the user according to the identity identifier of the user in the function navigation request; If the identity information of the user is verified, verify the validity of the function navigation request of the user; When the user's identity information verification fails, it is determined that the legitimacy verification of the function navigation request of the target function fails.

4. The method according to claim 3, characterized in that: The validating the function navigation request of the user includes: Verifying the validity of the request format and parameters of the function navigation request; If the request format and parameters in the function navigation request are correct, it is determined that the legitimacy verification of the function navigation request has passed; If there are errors in the request format and parameters in the function navigation request, it is determined that the legitimacy verification of the function navigation request fails.

5. The method according to any one of claims 1 to 4, characterized in that: The scenario definition information includes a semantic mapping relationship and context interaction information; the generating of the navigation strategy of the target function based on the function query information and the scenario definition information of each function of the target application program includes: Based on the semantic mapping relationship, determining standard function query information of the target function by performing semantic analysis on the function query information; The standard function query information is parsed through the context interaction information to determine the navigation strategy of the target function.

6. The method according to claim 5, characterized in that The context interaction information includes context logic information and reply rules; the parsing of the standard function query information through the context interaction information to determine the navigation strategy of the target function includes: Analyze the standard function query information according to the context logic information to determine module scheduling information; the module scheduling information includes a scheduling order of at least one processing module; Executing the processing modules in sequence according to the scheduling order of the at least one processing module to obtain execution results of the processing modules; According to the response rule, the execution results of each of the processing modules are integrated to obtain the navigation strategy of the target function.

7. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: According to the navigation strategy, the user is instructed to search for the target function by voice navigation.

8. A functional navigation device, characterized in that: The device comprises: An acquisition module, configured to acquire function query information of a target function in response to a function navigation request of a target function triggered by a user in a target application; A generating module, configured to generate a navigation strategy for the target function based on the function query information and the scenario definition information of each function of the target application; The search module is used to display the navigation strategy of the target function to instruct the user to search for the target function according to the navigation strategy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images