Information processing method and device, equipment, storage medium and program product

Abstract

The invention discloses an information processing method, and relates to the technical field of artificial intelligence. The method comprises the following steps: receiving item handling information sent by a first user; determining a target verbal skill template corresponding to the item handling information according to the item handling information, a preset standard verbal skill library and each personalized verbal skill library; determining a first execution node from the at least one node based on the execution sequence of each node, and taking the first execution node as a current node; determining a current node verbal skill corresponding to the current node according to the item handling information and the current node verbal skill template, and displaying the current node verbal skill; when the current node is not the execution ending node, determining a next execution node according to the verbal skill of the current node; and determining the next execution node as the current node, and repeatedly executing the step of determining the current node verbal skill corresponding to the current node according to the item handling information until the current node is an execution ending node. According to the scheme, the verbal skill determination flexibility and efficiency are improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of artificial intelligence technology, and in particular, to an information processing method, apparatus, device, storage medium, and program product. Background Art

[0002] With the development of artificial intelligence technology, the communication between enterprises and users is increasingly dependent on automated and standardized speech templates. Especially in the process of enterprises handling business for users, the design and application of speech templates need to be very precise and standardized.

[0003] Nowadays, most companies use fixed speech templates to communicate with users. These speech templates usually include predefined texts, questions, and replies. This method can quickly respond to user inquiries through speech templates. However, different sponsoring units of a company can handle different businesses, different ways of handling businesses, and different service features. This speech template is too fixed and cannot meet the personalized expression needs of different sponsoring units. It may lead to inconsistent user experience and even affect customer satisfaction. In addition, this method can only execute fixed speech templates step by step, and does not have the ability to dynamically adjust the speech template according to the real-time communication situation. It may result in repeated execution of inappropriate speech, which limits the fluency and efficiency of communication. Summary of the invention

[0004] The embodiments of the present invention provide an information processing method, apparatus, device, system and storage medium, which can meet the personalized expression needs of different hosting units, and can dynamically adjust the speech template according to the communication situation during the use of the speech template, provide users with appropriate speech, and improve the efficiency of business handling and user experience.

[0005] In a first aspect, an embodiment of the present invention provides an information processing method, including:

[0006] Receiving the matter handling information sent by the first user; the matter handling information includes the undertaking unit of the matter, the matter handling method and the matter identification;

[0007] Determine a target speech template corresponding to the matter handling information according to the matter handling information, a preset standard speech library and each personalized speech library; the target speech template includes at least one node, an execution order of each node and a node speech template corresponding to each node;

[0008] Determine a first execution node from the at least one node based on the execution order of the nodes, and use the first execution node as the current node;

[0009] Determine the current node speech corresponding to the current node according to the matter handling information and the current node speech template, and display the current node speech;

[0010] When the current node is not the end execution node, determining the next execution node according to the current node script;

[0011] The next execution node is determined as the current node, and the step of determining the current node speech corresponding to the current node according to the matter handling information is repeated until the current node is the end execution node.

[0012] In a second aspect, an embodiment of the present invention further provides an information processing device, the device comprising:

[0013] An information receiving module, used to receive the matter handling information sent by the first user; the matter handling information includes the undertaking unit of the matter, the matter handling method and the matter identification;

[0014] A template determination module is used to determine a target speech template corresponding to the matter handling information according to the matter handling information, a preset standard speech library and each personalized speech library; the target speech template includes at least one node, the execution order of each node and a node speech template corresponding to each node;

[0015] A first node determination module, configured to determine a first execution node from the at least one node based on the execution order of the nodes, and use the first execution node as the current node;

[0016] A speech determination module, used to determine the current node speech corresponding to the current node according to the matter handling information and the current node speech template, and display the current node speech;

[0017] A second node determination module, for determining a next execution node according to the current node script when the current node is not the end execution node;

[0018] The third node determination module is used to determine the next execution node as the current node, and repeatedly execute the step of determining the current node speech corresponding to the current node according to the matter handling information until the current node is the end execution node.

[0019] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an information processing method as described in any one of the embodiments of the present invention is implemented.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an information processing method as described in any one of the embodiments of the present invention.

[0021] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements an information processing method as described in any one of the embodiments of the present invention.

[0022] In the embodiment of the present invention, by combining the standard speech library and the personalized speech library, the organizer can provide the first user with a speech template that meets both corporate standards and personalized needs, thereby improving the flexibility of the speech template and user satisfaction. The next execution node is dynamically determined based on feedback information to avoid the repeated playback of meaningless speech due to unnecessary waiting and redundant steps in the execution of the speech template, thereby improving the flexibility of the speech template and improving the accuracy of the service and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A first flow chart of an information processing method provided by an embodiment of the present invention;

[0025] Figure 2 A schematic diagram of the structure of a speech template provided in an embodiment of the present invention;

[0026] Figure 3 A second flow chart of an information processing method provided by an embodiment of the present invention;

[0027] Figure 4 A flowchart of a method for creating a speech template provided by an embodiment of the present invention;

[0028] Figure 5 A schematic diagram of the structure of an information processing device provided by an embodiment of the present invention;

[0029] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0031] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations. It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. The purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or must use the relevant content of the solution.

[0032] Figure 1 This is the first flow chart of an information processing method provided by an embodiment of the present invention. The method of the embodiment of the present invention can meet the personalized expression needs of different hosting units, and can dynamically adjust the speech template according to the communication situation during the use of the speech template, provide users with appropriate speech, and improve the efficiency of business handling and user experience. The method can be executed by an information processing device provided by an embodiment of the present invention, and the device can be implemented in software and / or hardware. The following embodiments will be described by taking the device integrated in an electronic device as an example. The electronic device can be a computer device or a server, etc. Reference Figure 1 , the method may specifically include the following steps:

[0033] Step 101: Receive matter handling information sent by the first user.

[0034] Among them, the matter handling information includes the undertaking unit of the matter, the matter handling method and the matter identification. The first user can be a user who handles matters through the matter undertaking unit, or a staff member of the undertaking unit who assists the user in handling matters. The undertaking unit is the specific department or institution responsible for handling specific business matters. In different enterprises or organizational structures, the undertaking unit can be different departments under the head office, such as the Finance Department, Human Resources Department, etc.; in enterprises with a wide geographical distribution, the undertaking unit can also be a subsidiary or branch located in different regions. The matter handling methods include but are not limited to online handling, offline handling and self-service terminal handling. The matter identification is a unique identifier used to distinguish different business matters.

[0035] Specifically, different undertaking units have different matters that can be handled, ways of handling matters, and service characteristics. When the first user handles a business matter at the undertaking unit, the undertaking unit can guide the first user to handle the business matter quickly and efficiently through the corresponding words in the speech library of the undertaking unit for the business matter that the first user needs to handle. In an optional implementation, when the first user needs to handle a certain matter, the undertaking unit can send matter handling information to the undertaking unit through the business handling platform of the undertaking unit or the intelligent online customer service, and the undertaking unit can receive the matter handling information in real time, so as to determine the words used to guide the first user to handle the matter based on the matter handling information.

[0036] Step 102: determine the target speech template corresponding to the matter handling information according to the matter handling information, the pre-set standard speech library and each personalized speech library.

[0037] Among them, the target speech template includes at least one node, the execution order of each node, and the node speech template corresponding to each node. The standard speech library is used to store the standard speech templates of each matter. The standard speech template is a speech template uniformly stipulated by the enterprise and applicable to all undertaking units for handling matters. The personalized speech library is used to store the personalized speech templates of each matter, and different undertaking units correspond to different personalized speech libraries. The personalized speech template is a speech template pre-defined according to the service characteristics of the undertaking unit, and the personalized speech template can meet the personalized expression needs of different undertaking units. Since the standard speech template needs to be applicable to all undertaking units, the standard speech template only includes the speech of matters that can be handled by all undertaking units. For example, the first user handles the personal health examination at the self-service terminal of a certain undertaking unit. The health examination item is to obtain the health index of the first user based on the height and weight of the first user. Some undertaking units have instruments for measuring height and weight, while some undertaking units do not. Since the standard speech template needs to be applicable to all undertaking units, the standard speech template corresponding to the matter can be: "Please enter your height and weight". For the organizing unit that has the equipment to measure height and weight, the personalized script template for this matter can be: "Please go to the height and weight measuring instrument to measure your height and weight."

[0038] In order to improve the efficiency of handling matters for the first user, when the first user handles matters at the undertaking unit, the undertaking unit will first search for a speech template corresponding to the matter in its corresponding personalized speech library. When the speech template corresponding to the matter cannot be found in the personalized speech library, the speech template corresponding to the matter is searched from the standard speech library. In the embodiment of this scheme, optionally, determining the target speech template corresponding to the matter handling information according to the matter handling information, the pre-set standard speech library and each personalized speech library includes the following steps A1-A2:

[0039] Step A1: Search the target personalized speech template library corresponding to the undertaking unit of the matter in each personalized speech library; if the target personalized speech template library is found, search the target matter speech template of each handling method corresponding to the matter identifier in the target personalized speech template library. If the target matter speech template of each handling method is found, search the target speech template corresponding to the matter handling method in the target matter speech template of each handling method.

[0040] Among them, the target personalized speech template library is the personalized speech template library of the undertaking unit in the matter handling information. The target matter speech template is the speech template for each handling method of the matter to be handled by the first user in the personalized speech template library of the undertaking unit. The matter identification is a unique identifier used to distinguish different business matters. Matter handling methods include but are not limited to online handling, offline handling, and self-service terminal handling. Different handling methods of the same matter correspond to different speech templates. For example, the first user borrows a book at a library. When the first user handles it online through a mobile application or website, the speech template for book borrowing may include: "What kind of book do you want to borrow? You can use the search function or browse our book classification." When the first user borrows a book through a self-service terminal (library self-service machine), the speech template for book borrowing may include: "Please log in with your library card, and then select the book you want to borrow according to the prompts on the screen. After selecting the book, please place the book in the scanning area according to the instructions, and the system will automatically handle the borrowing procedures for you."

[0041] Specifically, after receiving the matter handling information, the undertaking unit determines its own personalized speech template library as the target personalized speech template library. According to the matter identifier, the target matter speech templates of all handling methods corresponding to the matter identifier are searched in the target personalized data template library. Exemplarily, the undertaking unit A receives the matter handling information, and the matter handling information includes: undertaking unit A, matter identifier m, and handling method is self-service terminal handling. If the undertaking unit A has a personalized speech template library, the speech library template is determined to be the target personalized speech template library. Search the target personalized speech template library for the target matter speech templates of each handling method of matter m. Filter out the speech template of the self-service terminal handling method from each target matter speech template, and determine it as the target speech template.

[0042] Step A2: If the target personalized speech template library cannot be found, or the target matter speech templates for each handling method corresponding to the matter identifier cannot be found, or the target speech template corresponding to the matter handling method cannot be found, then the target speech template is determined based on the standard speech library.

[0043] Specifically, the standard speech template is a speech template uniformly stipulated by the enterprise and is applicable to all undertaking units for handling matters. When the undertaking unit does not have a personalized speech template library; or the undertaking unit has a personalized speech template library, but the personalized speech template library does not contain an identifier that is the same as the item identifier of the first user's matter; or the personalized speech template library contains an identifier that is the same as the item identifier of the first user's matter, but the various speech templates under the identifier do not contain a processing method that is the same as the processing method of the first user's matter, the undertaking unit can directly search for the speech template corresponding to the processing method of the first user's matter in the standard speech library according to the item identifier, and determine it as the target speech template. If the speech template corresponding to the processing method of the first user's matter cannot be found in the standard speech library, the undertaking unit can directly send a prompt message to the first user to transfer to manual service, and send the prompt message to the staff and the first user so that the staff can handle matters for the first user.

[0044] In the above steps, the organizer will first search for the target speech template in the personalized speech library to provide a personalized service process for the first user, while meeting the organizer's personalized expression needs. When the personalized template is not available or applicable, the standard speech template provides a reliable backup option to ensure that the service will not be interrupted. By combining the standard speech library and the personalized speech library, the organizer can provide the first user with a speech template that meets corporate standards and takes into account personalized needs, which improves the flexibility of the speech template and user satisfaction.

[0045] Step 103: determine a first execution node from at least one node based on the execution order of each node, and use the first execution node as the current node.

[0046] Among them, the speech template is composed of nodes, each of which includes at least one node, the execution order of each node, and the node speech template corresponding to each node. A node can correspond to the handling steps of a matter, and the execution order of each node determines the handling process of the matter handled by the undertaking unit for the first user. The execution order ensures the continuity and logic of the service. The execution order of each node is not static. In the speech template of this solution, each node may be a decision point. Different branches are expanded according to the execution results of the handling steps corresponding to the decision point, thereby determining different subsequent nodes (the next node to be executed). According to the target speech template, the starting point of the matter handling is clarified to ensure the logic and continuity of the service process, which provides a solid foundation for the smooth progress of the entire service process.

[0047] For example, Figure 2 This is a schematic diagram of the structure of the speech template provided by the embodiment of the present invention. Figure 2 As shown, Figure 2Each circle in the figure represents a node, and the number in the node represents the node number. Figure 2 The arrows in the table are used to indicate the execution order of the nodes. If the current node is 2, the next node to be executed is 4. If the current node is 4, the next node to be executed is 6 or 5. Node 1 is the first execution node.

[0048] Step 104: determine the current node speech corresponding to the current node according to the matter handling information and the current node speech template, and display the current node speech.

[0049] Among them, the node speech template includes some fixed speech and / or content that needs to be filled dynamically. If a node speech template only includes fixed speech and does not include content that needs to be filled dynamically, the node speech corresponding to the node will be directly displayed. If the current node speech template also includes content that needs to be filled dynamically, the hosting platform can determine the content that needs to be filled dynamically in the current node speech template based on the feedback information of the first user on all executed nodes. After obtaining the content that needs to be filled dynamically, the current node speech is determined based on the fixed speech and dynamically filled content in the current node speech template, and the current node speech is displayed to the first user to guide the first user to handle matters.

[0050] According to the event handling information and the node speech template, the node speech can be quickly and accurately determined. By dynamically determining and displaying the speech, the system can communicate effectively with the user and guide the user to successfully complete the business handling. This not only improves the user experience, but also reduces the possibility of errors and confusion in the event handling process.

[0051] For example, after a library (organizer) receives the information on the handling of the matter, it determines the target speech template for the self-service terminal (the way to handle the matter) to handle the book borrowing matter in its personalized speech library. According to the execution order of each node of the target speech template, the first execution node is determined to be the current node. The speech template of the current node only includes the fixed speech of "Please enter the name of the book you want to borrow". Then the self-service terminal directly plays the speech of "Please enter the name of the book you want to borrow" for the user. After receiving the feedback information of the first user (the name of the book entered by the first user), it is determined that the current node has been executed. After receiving the speech, the user sends feedback information abc (name of the book) through the self-service terminal. If the current node is a node that shows the location of the book in the library to the user, the current node speech template is: XXX is on the XXXth floor, XXXth shelf, XXXth floor, and XXX is the content that needs to be dynamically filled. Then the self-service terminal can search for the location information of abc in the library database according to the feedback information (abc) of the previous node, and determine that abc is on the 3rd floor of the 3rd shelf on the 2nd floor according to the location information. Further, it is determined that the current node speech displayed for the first user is abc on the 3rd layer of the 3rd bookshelf on the 2nd floor.

[0052] Step 105: When the current node is not the end execution node, determine the next execution node according to the current node script.

[0053] The end execution node is the last executed node. After the end execution node is executed, the organizer will no longer execute other nodes in the target speech template. The end execution node can be preset or dynamically determined based on the feedback information of the first user on the executed node.

[0054] The speech template in this solution includes at least one node with an end mark. If a node carries an end mark, it means that the node is a fixed end execution node in the speech template. If the current node includes an end mark, the current node is determined to be an end execution node. For example Figure 2 Node 3 and node 6 in the list, there are no other executable nodes after these two nodes, and end markers can be added to these two nodes. In this solution, it is also possible to determine whether the current node is the end execution node based on the first user's feedback information on all executed nodes and the matter handling information. If the undertaking unit can automatically handle matters for the user based on the feedback information of all executed nodes, the current node can be determined to be the end execution node. Alternatively, if the first user marks the current node as the end execution node in the feedback information, the current node is determined to be the end execution node.

[0055] For example, the first user handles a book borrowing matter at a self-service terminal in a library. The user has entered the book to be borrowed, and the self-service terminal shows the user the shelf number of the book and the number of the book. The current node of the current node is "Do you need to show the roadmap? If you do, please press the Require button. If you do not, please press the Next button. If you need to exit, please press Exit." If the first user triggers the Exit button (the first user marks the current node as the end execution node in the feedback information), the current node is determined to be the end execution node.

[0056] Specifically, after displaying the current node speech and obtaining the corresponding feedback information, if the current node is the end execution node, exit the target speech template. If the current node is not the end execution node, determine the next node to be executed based on the first user's feedback information on the current node and the execution order of each node. In an optional implementation, the hosting platform cannot predict the specific feedback of the first user when designing the target speech template, so there may be some nodes in the target speech template that are not necessary to execute, or the order of each node in the target speech template is not the most reasonable order. In order to optimize the target speech template and improve the user experience, the hosting platform can adjust the execution process in real time according to the feedback information of the first user during the use of the target speech template, that is, determine the next execution node based on the comprehensive feedback information and the execution order of the nodes in the target speech template.

[0057] For example, the first user registers to borrow books at a self-service terminal. The first node in the target speech template is "Registering Borrowed Books Information", the second node is "Review of Borrowing Qualifications", and the third node is "Display of Borrowing Information". After executing the first node, the hosting platform searches the user database for the information of the first user corresponding to the user ID in the feedback information of the first node, and determines that the result of the review of the first user's borrowing qualifications is passed based on the information of the first user. Furthermore, the hosting platform can determine that the next execution node after the first node is "Display of Borrowing Information" instead of the original second node.

[0058] In the above steps, by dynamically determining the next execution node based on the feedback information, unnecessary waiting and redundant steps in the target speech template executed by the organizer can be avoided, thereby avoiding the repeated playback of meaningless speech. This not only improves the speed of determining the speech, but also improves the service efficiency and user satisfaction of the organizer.

[0059] Step 106: determine the next execution node as the current node, and repeat the step of determining the current node speech corresponding to the current node according to the matter handling information, until the current node is the end execution node.

[0060] Specifically, when the current node is not the end execution node, after determining the next execution node, the next executed node is used as the current node, the current node speech corresponding to the current node is determined in accordance with step 104, and the current node speech is displayed to the first user until the current node is the end execution node.

[0061] The technical solution of this embodiment receives the information of the matter handling sent by the first user; the matter handling information includes the undertaking unit of the matter, the matter handling method and the matter identification; the target speech template corresponding to the matter handling information is determined according to the matter handling information, the pre-set standard speech library and each personalized speech library; the target speech template includes at least one node, the execution order of each node and the node speech template corresponding to each node; the first execution node is determined from at least one node based on the execution order of each node, and the first execution node is used as the current node; the current node speech corresponding to the current node is determined according to the matter handling information and the current node speech template, and the current node speech is displayed; when the current node is not the end execution node, the next execution node is determined according to the current node speech; the next execution node is determined as the current node, and the step of determining the current node speech corresponding to the current node according to the matter handling information is repeated until the current node is the end execution node. The technical solution of this embodiment, by combining the standard speech library and the personalized speech library, the undertaking unit can provide the first user with a speech template that meets both corporate standards and personalized needs, thereby improving the flexibility of the speech template and user satisfaction. The next execution node is dynamically determined based on feedback information to avoid unnecessary waiting and redundant steps in the execution of the speech template, which would lead to repeated playback of meaningless speech. This improves the flexibility of the use of the speech template and enhances the user experience of the service accuracy.

[0062] Figure 3 This is a second flow chart of an information processing method provided by an embodiment of the present invention. This embodiment is a refinement based on the above embodiment. The specific method can be as follows Figure 3 As shown, the method may include the following steps:

[0063] Step 301: Receive matter handling information sent by the first user.

[0064] The matter handling information includes the undertaking unit of the matter, the matter handling method and the matter identification.

[0065] Step 302: determine the target speech template corresponding to the matter handling information according to the matter handling information, the pre-set standard speech library and each personalized speech library.

[0066] The target speech template includes at least one node, the execution order of each node, and the node speech template corresponding to each node.

[0067] Step 303: determine a first execution node from at least one node based on the execution order of each node, and use the first execution node as the current node.

[0068] Step 304: Perform template analysis on the current node speech template to obtain the static text and all placeholders of the current node speech template.

[0069] Among them, static text is the fixed text part in the current node speech template and does not rely on external data changes. For example, the fixed introductory words or explanatory text in the prompt information. The placeholder is a position marker in the current node speech template that needs to be dynamically filled with content according to the specific situation. Specifically, after determining the current node speech template, each element of the current node speech template is traversed to identify the placeholders in the current node speech template, so as to subsequently obtain the filling information corresponding to the placeholder. If the current node speech template only includes static text, the static text is determined as the current node speech.

[0070] Step 305: For each placeholder, if the filling information type identifier of the current placeholder is an interactive information identifier, the filling information of the current placeholder is obtained from the front-end server.

[0071] Each placeholder includes a corresponding fill information type identifier, and the fill information type identifier is an interactive information identifier or a loadable information identifier. Interactive information indicates that the fill information corresponding to the placeholder can only be determined based on the feedback information of the first user. The front-end server is a front-end page or voice receiver that can interact with the first user. The first user can send feedback information to the organizer through the front-end server, and the front-end server can receive and temporarily store the feedback information of the first user.

[0072] Specifically, if the fill-in information type of the current placeholder is identified as an interactive information identifier, the fill-in information of the current placeholder is searched in the feedback information of the first user stored in the front-end server. Exemplarily, the first user applies for book borrowing at a self-service terminal, and the processing step corresponding to the current node is the registration of borrowing information. The current node speech template includes: The number of XXX books that can be borrowed is YYY, how many books do you need to borrow? The fill-in information type of the XXX placeholder is identified as an interactive information identifier, and the fill-in content of the placeholder is the name of the book that the first user wants to borrow. The fill-in information of the placeholder can only be determined based on the feedback information stored in the front-end server.

[0073] Step 306: For each placeholder, if the fill information type identifier of the current placeholder is a loadable information identifier, determine the query identifier of the fill information of the current placeholder according to the fill information of other placeholders.

[0074] Among them, the loadable information indicates that the fill information of the current placeholder may be determined from the database of the hosting platform. The query identifier is used to uniquely identify specific information or records in a database or other data storage system. The query identifier in this solution can help the hosting platform quickly and accurately find the fill information of the current placeholder. Specifically, if the fill information type of the current placeholder is identified as a loadable information identifier, the query identifier of the fill information of the current placeholder can be determined based on the fill information of other placeholders whose fill information has been determined.

[0075] For example, the current node speech template includes: XXX (the filled content has been determined to be aaa) The number of books that can be borrowed is YYY, how many books do you want to borrow? Among them, YYY is the current placeholder, the filling information type identifier of the placeholder is the loadable information identifier, and the filling content of the placeholder is the number of XXX books remaining in the library. According to the filling information (aaa) of other placeholders, it can be determined that the query identifier of the current placeholder is aaa.

[0076] Step 307: Determine the data source corresponding to the filling information of the current placeholder based on the query identifier, and determine the filling information of the current placeholder through the data source.

[0077] The data source is a system used by the organizer to store data, such as the organizer's database and file system. Specifically, after determining the query identifier, the organizer determines the data source corresponding to the query identifier, searches for data corresponding to the fill information of the current placeholder in the corresponding data source, and determines the fill information of the current placeholder based on the data. For example, if the query identifier is a book name, the data source can be determined to be a database that records book information. If the query identifier is a user name, the data source can be determined to be a database that records user information.

[0078] In this scheme, optionally, the data source corresponding to the fill information of the current placeholder is determined based on the query identifier, and the fill information of the current placeholder is determined through the data source, including: querying the target loading information corresponding to the query identifier in all data of the data source; if the target loading information is queried, determining the fill information of the current placeholder based on the target loading information; if the target loading information is not queried, obtaining the fill information of the current placeholder from the front-end server.

[0079] The target loading information is information related to the query identifier in the data source. Specifically, after determining the query identifier and the data source, the query method is determined according to the type of the data source. For example, if the data source is a database system, a database query statement can be generated according to the query identifier, and the target loading information is searched in the data source through the database query statement. After obtaining the target loading information, the filling information of the current placeholder is sorted out from the target loading information.

[0080] If the target loading information cannot be found, it means that the organizer does not have the relevant information corresponding to the query identifier, or the first user's feedback information on the current node may be incorrect. The organizer can generate a prompt message, send the prompt message to the user through the front-end server, and receive the updated query identifier returned by the user in response to the prompt message through the front-end server. Alternatively, if the filling information corresponding to the current placeholder can be directly entered by the first user, when the target loading information cannot be found, the organizer can prompt the first user to directly fill in the filling information of the current placeholder through the front-end page.

[0081] For example, the fill information type of a placeholder is marked as a loadable information mark, and the content corresponding to the placeholder is the last payment information of the first user. After determining that the query mark is the user name, the organizer can search for the payment record corresponding to the user name in the payment database. If the organizer cannot find it, it means that the first user may not have paid the fee to the organizer before. In this case, the organizer can directly send a message to the user saying "Please enter the last payment information" so as to obtain the payment information filled in by the first user through the front-end server.

[0082] In this solution, through the acquisition of interactive information and dynamic processing of loadable information, the organizer can efficiently provide personalized services based on the specific situation of the first user. Automatically obtaining the fill-in information of the placeholder based on the loadable information identifier reduces the steps of unnecessary interaction with the first user and improves the efficiency of handling matters. At the same time, through accurate query identification and data source positioning, errors caused by inaccurate or incomplete information are avoided, greatly improving the efficiency, quality and user satisfaction of the service.

[0083] Step 308: Generate the current node speech based on the filling information and static text of each placeholder, and display the current node speech.

[0084] Specifically, after the filling information of each placeholder is determined, each placeholder is replaced one by one according to the filling information. After all placeholders are replaced, the placeholders are integrated with the static text in the speech template to obtain a complete, fluent and semantically clear speech for the current node.

[0085] Step 309: When the current node is not the end execution node, determine the next execution node according to the current node script; determine the next execution node as the current node, and repeat the step of determining the current node script corresponding to the current node according to the matter handling information until the current node is the end execution node.

[0086] Specifically, after displaying the current node, it is necessary to determine whether the current node is an end execution node. In this solution, optionally, determining whether the current node is an end execution node includes the following steps B1-B2:

[0087] Step B1: Obtain feedback information of the first user on the current node speech from the front-end server.

[0088] The front-end server is a front-end page or voice receiver that can interact with the first user. The first user can send feedback information to the organizer through the front-end server, and the front-end server can receive and temporarily store the feedback information of the first user. Specifically, after the organizer sends the current node speech to the first user, the organizer can receive the feedback information sent by the first user through the front-end server and determine whether to continue handling the matter according to the feedback information.

[0089] Step B2: If the feedback information includes an end mark, the current node is determined to be the end execution node; or: based on the feedback information of the first user on all executed execution nodes, determine whether the feedback information of the current node meets the processing end conditions determined in advance based on the matter processing information. If the feedback information of the current node meets the processing end conditions, the current node is determined to be the end execution node; or: if the current node is a predetermined fixed end node, the current node is determined to be the end execution node.

[0090] Among them, feedback information is used to instruct the undertaking unit whether to continue and how to handle the matter for the user. The end mark is used to instruct the undertaking unit to terminate the matter handling. The handling end condition is a condition predetermined by the undertaking unit and is used to determine whether the matter handling has been completed. The fixed end node is a mark pre-set in the speech template and is used to instruct the undertaking unit to terminate the matter handling.

[0091] Specifically, if the first user's feedback information for the current node speech includes an end mark, indicating that the first user does not need the organizer to continue to execute the target speech template, the current node is determined as the end execution node. For example, when a user is handling a book borrowing matter, the current node speech is "There are two versions of the aaa you want to borrow, please select the version you want to borrow." According to the normal execution process of the target speech template, the first user can choose the version to borrow, and the organizer can execute the next node according to the version to be borrowed feedback by the user. However, the first user directly clicks the exit button on the self-service terminal. After the organizer receives the feedback information corresponding to the end button, it determines that the feedback information includes an end mark, then the organizer can determine that the current node is the end execution node.

[0092] Alternatively, after receiving the feedback information of the first user, the feedback information of the executed nodes is summarized and sorted, and it is determined based on the sorting results that the subsequent nodes do not need to be executed to automatically complete the matter for the user, and the current node is determined as the end execution node. Exemplarily, the first user is applying for a loan, and the current node speech is: "Please enter your loan amount", and the organizer has determined the user identification information of the first user based on the feedback information of the executed nodes. After the first user feedbacks the loan amount for the current node speech, the step corresponding to the next node in the target speech template is to obtain the qualification information of the first user, and to review whether the first user can apply for a loan of the corresponding amount based on the qualification information. At this time, the organizer finds the qualification information of the first user in its user database based on the user identification information, and determines that the qualification review result is passed based on the qualification information. Further, the organizer has completed the loan processing business based on this information, so the current node is determined to be the end execution node.

[0093] Alternatively, if the current node is a fixed end node specified in the target speech template, the current node is determined to be the end execution node. For example, the first user is applying for a loan, and the organizer has determined the first user's qualification review results and loan amount and other information based on the executed nodes. The current node is the end execution node specified in the target speech template, and the current node speech is "Completed, thank you". After displaying the current node speech, the organizer ends the execution of the target speech template.

[0094] In the above steps, it is possible to dynamically determine whether to continue to execute the target speech template based on the feedback information of the first user. That is, the service process of this solution can be adjusted according to the actual needs of the user, rather than rigidly executing all preset steps. This method reduces the repetition of unnecessary operations and improves the efficiency of the service.

[0095] Specifically, after executing the end execution node, if the end execution node is not the fixed end node of the target speech template, it means that the execution order of each node in the target template cannot fully meet the needs of different first users. In order for the organizer to provide a smoother and more personalized user experience, in this solution, after displaying the node speech of the end execution node, it also includes: if the end execution node is not a predetermined fixed end node, obtain the execution information of all execution nodes, generate a sub-speech template of the target speech template based on the execution information of all execution nodes, and update the speech library where the target speech template is located based on the sub-speech template.

[0096] Among them, the execution information includes the execution order, the feedback information of the first user on each node, and the processing results of each node. The sub-speech template is a speech template after adjusting the nodes and the execution order of each node in the target speech template according to the feedback information of the first user. Specifically, after obtaining the execution information of all execution nodes, the organizing unit can analyze each node in the entire matter handling process to find the links that may lead to reduced efficiency or the parts with poor user feedback. According to this information, the nodes corresponding to the specific steps in the target speech template are adjusted, and the adjusted target speech template is determined as the sub-speech template of the Mu Bai speech template.

[0097] Through the above steps, the organizer can continuously improve and adapt to changes in user needs based on the feedback from the first user. By continuously optimizing the speech template, the organizer can provide more fluent and personalized speech templates, while improving the overall service efficiency and quality.

[0098] The technical solution of this embodiment receives the item handling information sent by the first user; the item handling information includes the undertaking unit of the item, the item handling method and the item identification; the target speech template corresponding to the item handling information is determined according to the item handling information, the pre-set standard speech library and each personalized speech library; the target speech template includes at least one node, the execution order of each node and the node speech template corresponding to each node; the first execution node is determined from at least one node based on the execution order of each node, and the first execution node is used as the current node; the current node speech template is analyzed to obtain the static text and all placeholders of the current node speech template; for each placeholder, if the filling information type identifier of the current placeholder is an interactive information identifier, the filling information of the current placeholder is obtained from the front-end server; if the filling information type identifier of the current placeholder is a loadable information identifier, the query identifier of the filling information of the current placeholder is determined according to the filling information of other placeholders; the data source corresponding to the filling information of the current placeholder is determined based on the query identifier, and the filling information of the current placeholder is determined through the data source. Display the current node speech. When the current node is not the end execution node, determine the next execution node according to the current node speech; determine the next execution node as the current node, and repeat the step of determining the current node speech corresponding to the current node according to the matter handling information until the current node is the end execution node. The technical solution of this embodiment can obtain the feedback information of the first user in real time through the front-end server, load and update the placeholder content from the data source according to the feedback information, and ensure the accuracy and timeliness of the speech provided by the organizer. At the same time, the organizer can flexibly adjust the node execution order of the speech template according to the user's feedback and the real-time situation of the matter handling, provide users with more accurate speech, avoid repeated playback of meaningless speech, improve the efficiency and quality of the service, and also improve user satisfaction.

[0099] Figure 4 The flowchart of the method for creating a speech template provided by the embodiment of the present invention is a refinement of the above embodiment. The specific method can be as follows Figure 4 As shown, the method may include the following steps:

[0100] Step 401: Receive new template information sent by a second user.

[0101] Among them, the new template information includes the new creation method, the matter information of the new template and the organizer; the matter information of the new template includes the matter handling method of the new template and the matter identification of the new template. The new creation method includes edit new creation and custom new creation. Edit new creation is to create a new speech template by editing an existing speech template. Custom new creation does not rely on the existing speech template, but uses the completely new creation method provided by the hosting platform to create a new speech template. The second user is the staff who creates the speech template.

[0102] Specifically, when the second user needs to create a speech template, the new template information can be sent to the organizer through the template creation platform of the organizer. The template creation platform includes a speech creation interface, and the second user can select the new creation method on the speech creation interface, and select the matter information of the matter to be handled by the new template in the speech creation interface. For example, click the "Create New Template" button on the management interface of the template creation platform. For example, a public service office wants to create a new speech template for its public consultation hotline. The administrator of the office (the second user) logs in to the template creation platform, selects "Create New Template", and fills in the following information through the form: New creation method: custom new creation; matter handling method: online handling; matter identification: service consultation; organizer: public service office. After the second user submits the form, the template creation platform can receive the new template information in the form. This process ensures that the organizer can correctly start a new template creation process based on the specific needs and instructions of the second user, while avoiding subsequent problems caused by incorrect data input.

[0103] Step 402: When the new creation mode is edit-new, the editing interface is determined according to the matter information of the new template and the organizing unit, and the editing interface is displayed to the second user.

[0104] Specifically, different undertaking units can handle different matters and provide different handling methods. Therefore, different undertaking units may correspond to different editing interfaces. The second user can create a new speech template based on the editing interface displayed by the undertaking unit. In this solution, optionally, when the creation method is to edit and create, the editing interface is determined based on the matter information of the newly created template and the undertaking unit, including the following steps C1 to C2:

[0105] Step C1: Determine a list of editable speech templates based on the matter information of the newly created template and the organizing unit, and display the list of editable speech templates to the second user.

[0106] The editable speech template list includes speech template identifiers corresponding to the matter identifier and the matter handling method, which can be edited by the second user. The second user can select one of the speech templates in the editable speech template list as the target editing template according to specific needs.

[0107] Specifically, a large number of speech templates are stored in the standard speech library and each personalized speech library, and different speech templates have different characteristics. For example, some speech templates in the standard speech library are fixed in form and cannot be edited. The speech templates in each personalized speech library also have different characteristics. For example, some greetings in the personalized speech templates in certain regions use local dialects. Even for the same matter, not all speech templates corresponding to the matter are suitable for the second user to edit the template. Therefore, in this solution, after determining the matter information of the newly created template, the template creation platform can first determine all personalized speech libraries suitable for the organizer according to the organizer corresponding to the newly created template. According to the matter identification and the matter handling method, the speech template suitable for the second user to edit and adjust is searched in the standard speech library and all personalized speech libraries, and an editable speech template list is generated according to the identification of these speech templates.

[0108] Step C2: Obtain a target editing template determined by the second user based on the list of editable speech templates; and generate an editing interface based on the target editing template.

[0109] Among them, the target editing template includes at least one node. The target editing template is the template selected by the second user in the list of editable speech templates. The editing interface can display the various nodes of the target editing template, the speech templates of each node, the execution order of each node, and the type information of each node. The second user can modify the order of each node and the node speech template of the target editing template in the editing interface, such as modifying the question text and adding new collection information. The editing interface in this solution usually includes a variety of interactive functions, such as dragging and dropping nodes to reorder, clicking nodes to view, editing details, and real-time preview of changes, etc., to facilitate users to complete editing work intuitively and flexibly.

[0110] This step ensures that the second user can access and modify the speech template suitable for his or her specific scenario, which not only improves the applicability and effectiveness of the speech template, but also enhances the second user experience and satisfaction.

[0111] Step 403: Receive various editing instructions sent by the second user based on the editing interface, and generate a new speech template based on the various editing instructions.

[0112] The editing instruction is an instruction sent by the second user to the template creation platform through the editing interface, which is used to instruct the template creation platform to modify the target editing template. In an optional implementation, the second user can perform a series of operations on the editing interface, such as adding new nodes, deleting existing nodes, modifying node content (such as question text, answer options), and adjusting node order, etc. Each operation will be captured by the template creation platform and converted into an editing instruction.

[0113] Specifically, different speech templates have different types of nodes, and different types of nodes correspond to different allowed operations. After the second user sends the editing instruction, the template creation platform can review the editing execution to determine whether the editing instruction sent by the second user can be executed. In this solution, optionally, a new speech template is generated based on each editing instruction, including the following steps D1-D2:

[0114] Step D1: review each editing instruction according to the node type of the editing node corresponding to the editing instruction to obtain a review result.

[0115] Among them, the node type is an ordinary node or a fixed node. An ordinary node is a node without special requirements, and a fixed node is a node with special requirements. The second user cannot modify the fixed node at will. Specifically, after receiving the edit execution, the speech creation platform can review each edit execution according to the node type to determine whether the edit execution order can be executed. In this scheme, optionally, each edit instruction is reviewed according to the node type of the edit node corresponding to the edit instruction to obtain the review result, including: when the node type is an ordinary node, the edit instruction is to add a node or delete a node or edit a node, the review result of the edit instruction is determined to be approved; when the node type is a fixed node, the edit instruction is to delete a node or edit the node speech information, the review result of the edit instruction is determined to be unsuccessful; when the node type is a fixed node, the edit instruction is to add a node or edit the node basic information, the review result of the edit instruction is determined to be approved.

[0116] Among them, the node information includes node basic information and node wording information. The node basic information is pre-defined by the organizer and can be modified by the second user, including the node execution order and node name, etc. Specifically, if the node to be edited by the second user is a common node, it means that the user can delete the node or add a new node before or after the node, and can also modify the node wording of the node, etc. Therefore, when the node type is a common node and the editing instruction is to add a node, delete a node, or edit a node, the audit result of the editing instruction is determined to be approved.

[0117] If the node that the second user wants to edit is a fixed node, it means that the second user can only add a new node before or after the node, but cannot delete the node or modify the node's speech information. Therefore, when the node type is a fixed node and the editing instruction is to delete the node or edit the node's speech information, the audit result of the editing instruction is determined to be failed; when the node type is a fixed node and the editing instruction is to add a new node or edit the node's basic information, the audit result of the editing instruction is determined to be passed. For example, a speech template includes a node for a statement of precautions. The speech in the node used to remind the user of precautions cannot be changed at will, so the node has been marked as a fixed node during design. If the second user's editing instruction is to modify the speech content, it can be determined that the audit result of the editing instruction is failed.

[0118] Step D2: When the audit result is passed, execute the editing instruction and generate a new speech template based on the executed editing instruction; when the audit result is failed, generate prompt information according to the editing instruction, and send the prompt information to the second user, so that the second user can modify the editing instruction based on the prompt information.

[0119] Specifically, when the audit result of an editing instruction is approved, the template creation platform will directly execute the editing instruction and generate a new speech template based on each node after the execution of the editing instruction. The new speech template includes all the modifications that have been reviewed and executed to ensure that its structure, content and logic meet the business needs and the expectations of the second user. If the audit result of an editing instruction is unsuccessful, the template creation platform will generate a prompt message, which includes the editing instruction that failed the review and the specific reasons for failure, such as fixed nodes cannot be deleted or edited, or some editing content may violate business rules. After the prompt information is determined, the prompt information is sent to the second user in a timely manner so that the second user can modify the editing instruction based on the prompt information.

[0120] In this way, the quality and compliance of the speech template can be ensured. At the same time, through the feedback mechanism, the second user can efficiently realize the design of the target template, and can respond quickly and make appropriate adjustments even when facing failure in the review.

[0121] Step 404: When the new creation mode is custom creation, the custom element corresponding to the organizer of the new template information is determined according to the pre-determined custom elements of each organizer.

[0122] Among them, custom elements are elements of the newly created speech template that the second user can customize, such as the nodes, node speech templates, node order, and template names that the second user can add corresponding to the matter handling information. Different matters correspond to different custom elements. For example, for book borrowing matters, the custom elements may include custom elements such as the book borrowing registration node and the borrowing qualification review node. Specifically, when the new creation method is selected as custom creation, the template creation platform can determine the organizer and matter information based on the matter handling information, and determine the custom elements of the organizer corresponding to the newly created template based on the organizer and matter information.

[0123] Step 405: Generate a custom operation list according to the custom elements corresponding to the undertaking unit of the newly created template information and the matter information of the newly created template.

[0124] Among them, the custom operation list includes elements that can be operated by the second user corresponding to the matter identification and the matter handling method. Specifically, different organizing units, different matters to be handled, and different matter handling methods correspond to different custom elements. After determining the new template information, the template creation platform can filter out the custom elements corresponding to the matters to be handled and the matter handling methods from the custom elements corresponding to the organizing unit, and generate a custom operation list based on them. For example, for the health department, the custom operation list may include health risk warning nodes, health policy information nodes, and health question and answer process nodes.

[0125] Step 406: Generate and display a customized new interface based on the customized operation list, display the customized new interface to the second user, and receive a new speech template customized by the second user based on the customized new interface.

[0126] Specifically, after determining the custom operation list, the template creation platform can dynamically generate a custom new interface based on the custom operation list. The custom new interface includes various editable fields, options and modules, and the second user can create a new speech template by adding, deleting or modifying the custom elements in the custom operation list. After the second user completes editing the template using the custom new interface, the template creation platform can receive the second user's operation information on the new interface and determine the new speech template based on the operation information.

[0127] Step 407: store the newly created speech template in the speech library corresponding to the hosting unit of the newly created template information.

[0128] The speech library includes a standard speech library or a personalized speech library. The organizer is the organizer corresponding to the new speech template created by the second user. Specifically, after determining the new speech template, the template creation platform stores the new speech template in the corresponding speech library.

[0129] The technical solution of this embodiment is to receive the new template information sent by the second user, and the new template information includes the new creation method, the matter information of the new template and the organizer; the matter information of the new template includes the matter handling method of the new template and the matter identification of the new template. When the new creation method is edit new creation, the editing interface is determined according to the matter information of the new template and the organizer, and the editing interface is displayed to the second user. Receive each editing instruction sent by the second user based on the editing interface, and generate a new speech template based on each editing instruction. Store the new speech template in the speech library corresponding to the organizer, and the speech library includes a standard speech library or a personalized speech library. When the new creation method is custom new creation, determine the custom element corresponding to the organizer of the new template information according to the custom elements of each organizer determined in advance; generate a custom operation list according to the custom element corresponding to the organizer of the new template information and the matter information of the new template; generate and display a custom new interface according to the custom operation list; display the custom new interface to the second user, and receive the new speech template customized by the second user based on the custom new interface; store the new speech template in the speech library corresponding to the organizer of the new template information. The technical solution of this embodiment provides two modes: edit and create, and customize and create. The second user can choose the most suitable mode to create a speech template according to his needs and preferences, thereby improving the flexibility and efficiency of template construction. The accuracy of the newly created speech template is ensured through the editing interface and operation guidance, which reduces the errors caused by manual operation and improves the efficiency and quality of speech template construction.

[0130] Figure 5 The structure diagram of an information processing device provided by an embodiment of the present invention is suitable for executing the information processing method provided by an embodiment of the present invention. Figure 5 As shown, the device may specifically include:

[0131] The information receiving module 501 is used to receive the event handling information sent by the first user; the event handling information includes the undertaking unit of the event, the event handling method and the event identification;

[0132] The template determination module 502 is used to determine the target speech template corresponding to the matter handling information according to the matter handling information, the preset standard speech library and each personalized speech library; the target speech template includes at least one node, the execution order of each node and the node speech template corresponding to each node;

[0133] A first node determination module 503, configured to determine a first execution node from the at least one node based on the execution order of the nodes, and use the first execution node as the current node;

[0134] A speech determination module 504 is used to determine the current node speech corresponding to the current node according to the matter handling information and the current node speech template, and display the current node speech;

[0135] A second node determination module 505, configured to determine a next execution node according to the current node script when the current node is not the end execution node;

[0136] The third node determination module 506 is used to determine the next execution node as the current node, and repeatedly execute the step of determining the current node speech corresponding to the current node according to the matter handling information until the current node is the end execution node.

[0137] Optionally, the template determination module 502 is specifically used to: search for a target personalized speech template library corresponding to the undertaking unit of the matter in each personalized speech library;

[0138] If the target personalized speech template library is found, searching the target item speech templates for each handling method corresponding to the item identifier in the target personalized speech template library;

[0139] If the target matter speech templates of the various handling methods are found, the target matter speech templates corresponding to the matter handling method are searched among the target matter speech templates of the various handling methods.

[0140] Optionally, the template determination module 502 is also used to: if the target personalized speech template library cannot be found, or the target matter speech templates for each handling method corresponding to the matter identifier cannot be found, or the target speech template corresponding to the matter handling method cannot be found, then determine the target speech template according to the standard speech library.

[0141] Optionally, the speech determination module 504 is specifically used to: perform template analysis on the current node speech template to obtain the static text and all placeholders of the current node speech template;

[0142] Obtaining filling information of each placeholder according to the filling information type identifier of each placeholder; wherein the filling information type identifier is an interactive information identifier or a loadable information identifier;

[0143] The current node speech is generated based on the filling information of each placeholder and the static text.

[0144] Optionally, the speech determination module 504 is further configured to: for each placeholder, if the filling information type identifier of the current placeholder is the interactive information identifier, obtain the filling information of the current placeholder from the front-end server;

[0145] If the filling information type identifier of the current placeholder is the loadable information identifier, determine the query identifier of the filling information of the current placeholder according to the filling information of other placeholders;

[0146] The data source corresponding to the filling information of the current placeholder is determined based on the query identifier, and the filling information of the current placeholder is determined through the data source.

[0147] Optionally, the speech determination module 504 is further used to: query all data of the data source for target loading information corresponding to the query identifier;

[0148] If the target loading information is found, then the filling information of the current placeholder is determined according to the target loading information;

[0149] If the target loading information cannot be found, the filling information of the current placeholder is obtained from the front-end server.

[0150] Optionally, the second node determination module 505 is specifically configured to: obtain feedback information of the first user on the current node speech from the front-end server;

[0151] If the feedback information includes an end identifier, determining the current node as the end execution node; or:

[0152] Determine, based on the first user's feedback information on all executed execution nodes, whether the feedback information of the current node meets the handling end condition determined in advance based on the matter handling information; if the feedback information of the current node meets the handling end condition, determine the current node as the end execution node; or:

[0153] If the current node is a predetermined fixed end node, the current node is determined as the end execution node.

[0154] Optionally, the second node determination module 505 is further configured to: if the end execution node is not the predetermined fixed end node, obtain execution information of all execution nodes, wherein the execution information includes an execution order;

[0155] A sub-speech template of the target speech template is generated according to the execution information of all execution nodes, and the speech library where the target speech template is located is updated based on the sub-speech template.

[0156] Optionally, the template determination module 502 is specifically configured to: receive new template information sent by the second user, wherein the new template information includes a new creation method, event information of the new template, and an undertaking unit; the event information of the new template includes an event handling method of the new template and an event identifier of the new template;

[0157] When the new creation mode is edit new creation, an editing interface is determined according to the event information of the new template and the organizer, and the editing interface is displayed to the second user;

[0158] Receiving each editing instruction sent by the second user based on the editing interface, and generating a new speech template based on the each editing instruction;

[0159] The newly created speech template is stored in the speech library corresponding to the organizing unit of the newly created template information.

[0160] Optionally, the template determination module 502 is further used to: determine a list of editable speech templates according to the event information of the newly created template and the organizer, and display the list of editable speech templates to the second user;

[0161] Acquire a target editing template determined by the second user based on the editable speech template list; wherein the target editing template includes at least one node;

[0162] The editing interface is generated based on the target editing template.

[0163] Optionally, the template determination module 502 is further used to: review each editing instruction according to the node type of the editing node corresponding to the editing instruction to obtain a review result; the node type is a common node or a fixed node;

[0164] When the audit result is passed, the editing instruction is executed, and the new speech template is generated based on the executed editing instruction;

[0165] When the audit result is that the audit fails, prompt information is generated according to the editing instruction, and the prompt information is sent to the second user, so that the second user modifies the editing instruction based on the prompt information.

[0166] Optionally, the template determination module 502 is further configured to: when the node type is the common node and the editing instruction is the adding node or the deleting node or the editing node, determine that the review result of the editing instruction is review passed;

[0167] When the node type is the fixed node and the editing instruction is the node deletion or the node editing speech information, determining that the review result of the editing instruction is review failure;

[0168] When the node type is the fixed node and the editing instruction is to add a new node or to edit basic node information, it is determined that the review result of the editing instruction is approved.

[0169] Optionally, the template determination module 502 is further used to: when the new creation mode is custom creation, determine the custom element corresponding to the organizer of the new template information according to the pre-determined custom elements of each organizer;

[0170] Generate a custom operation list according to the custom elements corresponding to the organizer of the newly created template information and the matter information of the newly created template;

[0171] Generate and display a custom new creation interface according to the custom operation list;

[0172] The customized new creation interface is displayed to the second user, and a new speech template customized by the second user based on the customized new creation interface is received.

[0173] The information processing device provided in the embodiment of the present invention can execute the information processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For the contents not described in detail in this embodiment, reference can be made to the description in any method embodiment of the present invention.

[0174] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, referring to Figure 6 , Figure 6 The electronic device 12 shown is only an example and should not limit the functions and scope of use of the embodiments of the present application. Figure 6 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0175] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0176] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0177] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 6 not shown, usually called a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0178] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0179] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0180] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, to implement an information processing method provided by an embodiment of the present invention: receiving the matter handling information sent by the first user; the matter handling information includes the undertaking unit of the matter, the matter handling method and the matter identification; determining the target speech template corresponding to the matter handling information according to the matter handling information, a pre-set standard speech library and each personalized speech library; the target speech template includes at least one node, the execution order of each node and the node speech template corresponding to each node; determining the first execution node from the at least one node based on the execution order of each node, and taking the first execution node as the current node; determining the current node speech corresponding to the current node according to the matter handling information and the current node speech template, and displaying the current node speech; when the current node is not the end execution node, determining the next execution node according to the current node speech; determining the next execution node as the current node, and repeating the step of determining the current node speech corresponding to the current node according to the matter handling information until the current node is the end execution node.

[0181] The embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, an information processing method provided by all the embodiments of the present invention is implemented: receiving a matter handling information sent by a first user; the matter handling information includes the undertaking unit of the matter, the matter handling method and the matter identification; determining the target speech template corresponding to the matter handling information according to the matter handling information, a preset standard speech library and each personalized speech library; the target speech template includes at least one node, the execution order of each node and the node speech template corresponding to each node; determining the first execution node from the at least one node based on the execution order of each node, and taking the first execution node as the current node; determining the current node speech corresponding to the current node according to the matter handling information and the current node speech template, and displaying the current node speech; when the current node is not the end execution node, determining the next execution node according to the current node speech; determining the next execution node as the current node, and repeating the step of determining the current node speech corresponding to the current node according to the matter handling information until the current node is the end execution node. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer readable storage media can be, for example, but not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor electronic devices, devices or components, or any combination thereof. More specific examples of computer readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction-executing electronic device, device, or component.

[0182] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction-executing electronic device, apparatus, or device.

[0183] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0184] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0185] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements an information processing method as provided in any embodiment of the present application.

[0186] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0187] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An information processing method, characterized in that: include: Receiving the matter handling information sent by the first user; the matter handling information includes the undertaking unit of the matter, the matter handling method and the matter identification; Determine the target speech template corresponding to the matter handling information according to the matter handling information, the pre-set standard speech library and each personalized speech library; The target speech template includes at least one node, the execution order of each node and the node speech template corresponding to each node; Determine a first execution node from the at least one node based on the execution order of the nodes, and use the first execution node as the current node; Determine the current node speech corresponding to the current node according to the matter handling information and the current node speech template, and display the current node speech; When the current node is not the end execution node, determining the next execution node according to the current node script; The next execution node is determined as the current node, and the step of determining the current node speech corresponding to the current node according to the matter handling information is repeated until the current node is the end execution node.

2. The method according to claim 1, characterized in that Determining a target speech template corresponding to the matter handling information according to the matter handling information, a preset standard speech library and each personalized speech library, including: Searching for a target personalized speech template library corresponding to the undertaking unit of the matter in each personalized speech library; If the target personalized speech template library is found, searching the target item speech templates for each handling method corresponding to the item identifier in the target personalized speech template library; If the target matter speech templates of the various handling methods are found, the target matter speech templates corresponding to the matter handling method are searched among the target matter speech templates of the various handling methods.

3. The method according to claim 2, characterized in that The method further comprises: If the target personalized speech template library cannot be found, or the target matter speech templates for each handling method corresponding to the matter identifier cannot be found, or the target speech template corresponding to the matter handling method cannot be found, then the target speech template is determined according to the standard speech library.

4. The method according to claim 1, characterized in that Determining the current node speech corresponding to the current node according to the matter handling information and the current node speech template includes: Performing template analysis on the current node speech template to obtain static text and all placeholders of the current node speech template; Obtaining filling information of each placeholder according to the filling information type identifier of each placeholder; wherein the filling information type identifier is an interactive information identifier or a loadable information identifier; The current node speech is generated based on the filling information of each placeholder and the static text.

5. The method according to claim 4, characterized in that According to the fill information type identifier of each placeholder, the fill information of each placeholder is obtained respectively, including: For each placeholder, if the filling information type identifier of the current placeholder is the interactive information identifier, obtaining the filling information of the current placeholder from the front-end server; If the filling information type identifier of the current placeholder is the loadable information identifier, determine the query identifier of the filling information of the current placeholder according to the filling information of other placeholders; The data source corresponding to the filling information of the current placeholder is determined based on the query identifier, and the filling information of the current placeholder is determined through the data source.

6. The method according to claim 5, characterized in that Determining fill information of the current placeholder through the data source includes: Searching for target loading information corresponding to the query identifier in all data of the data source; If the target loading information is found, then the filling information of the current placeholder is determined according to the target loading information; If the target loading information cannot be found, the filling information of the current placeholder is obtained from the front-end server.

7. The method according to claim 1, characterized in that After displaying the current node speech, the method further includes: Acquire feedback information of the first user on the current node speech from the front-end server; If the feedback information includes an end identifier, determining the current node as the end execution node; or: Determine, based on the first user's feedback information on all executed execution nodes, whether the feedback information of the current node meets the handling end condition determined in advance based on the matter handling information; if the feedback information of the current node meets the handling end condition, determine the current node as the end execution node; or: If the current node is a predetermined fixed end node, the current node is determined as the end execution node.

8. The method according to claim 7, characterized in that The method further comprises: If the end execution node is not the predetermined fixed end node, acquiring execution information of all execution nodes, wherein the execution information includes an execution order; A sub-speech template of the target speech template is generated according to the execution information of all execution nodes, and the speech library where the target speech template is located is updated based on the sub-speech template.

9. The method according to claim 1, characterized in that: Before receiving the matter handling information sent by the first user, the method further includes: Receiving new template information sent by the second user, the new template information including the new creation method, the matter information of the new template and the undertaking unit; the matter information of the new template includes the matter handling method of the new template and the matter identifier of the new template; When the new creation mode is edit new creation, an editing interface is determined according to the event information of the new template and the organizer, and the editing interface is displayed to the second user; Receiving each editing instruction sent by the second user based on the editing interface, and generating a new speech template based on the each editing instruction; The newly created speech template is stored in the speech library corresponding to the organizing unit of the newly created template information.

10. The method according to claim 9, characterized in that The editing interface is determined according to the event information and the organizer of the newly created template, including: Determine a list of editable speech templates according to the event information of the newly created template and the organizer, and display the list of editable speech templates to the second user; Acquire a target editing template determined by the second user based on the editable speech template list; wherein the target editing template includes at least one node; The editing interface is generated based on the target editing template.

11. The method according to claim 9, characterized in that The editing instructions include adding a new node, deleting a node and editing a node. The editing node includes editing node speech information and editing node basic information. A new speech template is generated based on each editing instruction, including: Auditing each editing instruction according to the node type of the editing node corresponding to the editing instruction to obtain an audit result; the node type is a common node or a fixed node; When the audit result is passed, the editing instruction is executed, and the new speech template is generated based on the executed editing instruction; When the audit result is that the audit fails, prompt information is generated according to the editing instruction, and the prompt information is sent to the second user, so that the second user modifies the editing instruction based on the prompt information.

12. The method according to claim 11, characterized in that Each editing instruction is reviewed according to the node type of the editing node corresponding to the editing instruction to obtain a review result, including: When the node type is the common node and the editing instruction is the adding node or deleting the node or editing the node, determining that the review result of the editing instruction is review passed; When the node type is the fixed node and the editing instruction is the node deletion or the node editing speech information, determining that the review result of the editing instruction is review failure; When the node type is the fixed node and the editing instruction is to add a new node or to edit basic node information, it is determined that the review result of the editing instruction is approved.

13. The method according to claim 9, characterized in that The method further comprises: When the new creation mode is custom creation, the custom element corresponding to the organizer of the new template information is determined according to the pre-determined custom elements of each organizer; Generate a custom operation list according to the custom elements corresponding to the organizer of the newly created template information and the matter information of the newly created template; Generate and display a custom new creation interface according to the custom operation list; The customized new creation interface is displayed to the second user, and a new speech template customized by the second user based on the customized new creation interface is received.

14. An information processing device, characterized in that: include: An information receiving module, used to receive the matter handling information sent by the first user; The matter handling information includes the undertaking unit of the matter, the matter handling method and the matter identification; A template determination module, used to determine a target speech template corresponding to the matter handling information according to the matter handling information, a preset standard speech library and each personalized speech library; The target speech template includes at least one node, the execution order of each node and the node speech template corresponding to each node; A first node determination module, configured to determine a first execution node from the at least one node based on the execution order of the nodes, and use the first execution node as the current node; A speech determination module is used to determine the current node speech corresponding to the current node according to the matter handling information and the current node speech template, and display the current node speech; A second node determination module, for determining a next execution node according to the current node script when the current node is not the end execution node; The third node determination module is used to determine the next execution node as the current node, and repeatedly execute the step of determining the current node speech corresponding to the current node according to the matter handling information until the current node is the end execution node.

15. An information processing electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the information processing method according to any one of claims 1 to 13 when executing the computer program.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the information processing method according to any one of claims 1 to 13 is implemented.

17. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the information processing method according to any one of claims 1 to 13.

Images