Text robot answering method and device, processor and storage medium

Abstract

The application provides a text robot answering method and device, a processor and a storage medium, and belongs to the field of text robot answering. The text robot answering method applied to a client comprises the following steps: generating inquiry information and sending the inquiry information to a text robot; when it is determined that the reply information received from the text robot is a customer information acquisition instruction, acquiring customer information attributes, determining a corresponding information acquisition mode; acquiring customer information according to the information acquisition mode, generating a customer information acquisition result, and sending the customer information acquisition result to the text robot; wherein the reply information is generated by the text robot based on the inquiry information; and feedback information received from the text robot in response to the customer information acquisition result is displayed to the customer. Through the method provided by the application, a more customer-actual-situation-fitting reply can be provided, the customer reply accuracy is improved, the modification range is reduced, and the input cost of the text robot reply is reduced.

Description

Technical Field

[0001] This application relates to the field of text robot response technology, specifically to a text robot response method, a text robot response device, a processor, and a storage medium. Background Technology

[0002] With the development of mobile internet, mobile banking applications on mobile devices have replaced offline branches, becoming the preferred channel for most users to conduct banking business. When encountering problems while using mobile banking, customers often choose to ask online customer service for support. Due to limited human agent resources, most applications offer chatbot services to answer customer questions. Only when the chatbot cannot answer the customer's question are they transferred to a human customer service representative for accurate responses.

[0003] In existing technologies, text robots typically respond to customer questions using fixed scripts, failing to provide more tailored answers based on customer information. Achieving this effect requires modifying the text robot, but such modifications are difficult and increase costs. Summary of the Invention

[0004] The purpose of this application is to provide a text robot response method, apparatus, processor, and storage medium.

[0005] To achieve the above objectives, a first aspect of this application provides a text robot response method applied to a client, comprising: generating inquiry information based on user input and sending the inquiry information to a text robot; if a response received from the text robot is a customer information retrieval instruction, acquiring customer information attributes and determining an information retrieval method corresponding to the customer information attributes; acquiring customer information according to the information retrieval method corresponding to the customer information attributes, generating a customer information retrieval result, and sending the customer information retrieval result to the text robot; wherein the response information is generated by the text robot based on the inquiry information; and displaying feedback information received from the text robot regarding the customer information retrieval result to the customer.

[0006] In this embodiment of the application, the response information is generated by a text robot in the following manner: in response to a received query, semantic analysis is performed on the query to obtain a semantic analysis result; the response information corresponding to the semantic analysis result is matched in a pre-configured knowledge base; the response information includes a customer information retrieval instruction and a display response information.

[0007] In this embodiment of the application, the method further includes: if it is determined that the reply information received from the text robot is display reply information, directly displaying the display reply information to the customer.

[0008] In this embodiment of the application, the displayed response information is configured as a text format.

[0009] In this embodiment of the application, the customer information retrieval instruction and the customer information retrieval result are configured as identifiers.

[0010] In this embodiment of the application, sending the customer information acquisition result to the text robot includes: if it is determined that the customer information acquisition result is successful, determining the attributes of the customer information carried in the customer information acquisition result; determining the encryption method of the customer information acquisition result according to the attributes of the customer information; encrypting the customer information acquisition result according to the determined encryption method; and sending the encrypted customer information acquisition result to the text robot.

[0011] In this embodiment of the application, the feedback information is generated by the text robot in the following manner: if it is determined that the customer information acquisition result is successful, feedback information is assembled based on the customer information carried in the customer information acquisition result; if it is determined that the customer information acquisition result is unsuccessful, feedback information is generated to instruct the customer to open the customer information acquisition permission.

[0012] A second aspect of this application provides a text robot response method, applied to a text robot, comprising: generating response information based on query information received from a client, and sending the response information to the client; wherein the query information is generated by the client based on user input; generating feedback information based on customer information acquisition results received from the client, and sending the feedback information to the client for display to the customer; wherein, when the client determines that the response information is a customer information acquisition instruction, it acquires customer information attributes, determines an information acquisition method corresponding to the customer information attributes; acquires customer information according to the information acquisition method corresponding to the customer information attributes, and generates a customer information acquisition result.

[0013] In this embodiment of the application, generating response information based on the query information received from the client includes: responding to the received query information by performing semantic analysis on the query information to obtain a semantic analysis result; matching the response information corresponding to the semantic analysis result in a pre-configured knowledge base; the response information includes a customer information retrieval instruction and a display response information.

[0014] In this embodiment of the application, generating feedback information based on the customer information acquisition result received from the client includes: if the customer information acquisition result is determined to be successful, assembling feedback information according to the customer information carried in the customer information acquisition result; if the customer information acquisition result is determined to be unsuccessful, generating feedback information to instruct the customer to grant customer information acquisition permission.

[0015] A third aspect of this application provides a text robot response device, the text robot response device comprising: a client, configured to: generate and send query information based on user input; if the received response information is a customer information retrieval instruction, acquire customer information attributes and determine an information retrieval method corresponding to the customer information attributes; acquire customer information according to the information retrieval method corresponding to the customer information attributes, generate a customer information retrieval result, and send the customer information retrieval result; and display the received feedback information regarding the customer information retrieval result to the customer.

[0016] A text robot is used to: generate and send response information based on received inquiry information; and generate and send feedback information based on received customer information retrieval results.

[0017] In this embodiment of the application, generating response information based on received inquiry information includes: performing semantic analysis on the inquiry information to obtain semantic analysis results; matching response information corresponding to the semantic analysis results in a pre-configured knowledge base; the response information includes customer information retrieval instructions and display response information.

[0018] In this embodiment of the application, sending the customer information acquisition result includes: if it is determined that the customer information acquisition result is successful, determining the attributes of the customer information carried in the customer information acquisition result; determining the encryption method of the customer information acquisition result according to the attributes of the customer information; encrypting the customer information acquisition result according to the determined encryption method; and sending the encrypted customer information acquisition result.

[0019] In this embodiment of the application, generating feedback information based on the received customer information acquisition result includes: if the customer information acquisition result is determined to be successful, assembling feedback information based on the customer information carried in the customer information acquisition result; if the customer information acquisition result is determined to be unsuccessful, generating feedback information to instruct the customer to grant customer information acquisition permission.

[0020] A fourth aspect of this application provides a processor configured to execute the text robot response method applied to a client as described above, or configured to execute the text robot response method applied to a text robot as described above.

[0021] A fifth aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the text robot response method applied to a client as described above, or to perform the text robot response method applied to a text robot as described above.

[0022] The sixth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the text robot response method applied to a client as described above, or is configured to execute the text robot response method applied to a text robot as described above.

[0023] The technical solution provided in this application has at least the following technical effects:

[0024] The text robot response method of this application involves the following steps: When a user inputs data through a client, the client generates a query based on the user's input and sends the query to the text robot. The text robot generates a response based on the query and sends the response to the client. If the client determines that the response is a customer information retrieval instruction, it determines the customer information retrieval result based on the instruction and sends the result to the text robot. The text robot generates feedback based on the customer information retrieval result, sends the feedback to the client, and displays the feedback to the customer through the client. The method provided in this application can provide responses that are more tailored to the customer's actual situation, improve the accuracy of customer responses, reduce the scope of modifications, and lower the investment cost of text robot response.

[0025] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0026] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0027] Figure 1 A flowchart illustrating a text robot response method applied to a client according to an embodiment of this application is shown schematically;

[0028] Figure 2A flowchart illustrating a text robot response method applied to a text robot according to an embodiment of this application is shown schematically;

[0029] Figure 3 A schematic diagram of a text robot response device according to an embodiment of this application is shown;

[0030] Figure 4 The diagram illustrates the internal structure of a computer device according to an embodiment of this application.

[0031] Explanation of reference numerals in the attached figures

[0032] 300 - Text robot response device; 301 - Client; 302 - Text robot; A01 - Processor; A02 - Network interface; A03 - Internal memory; A04 - Non-volatile storage medium; B01 - Operating system; B02 - Computer program. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0034] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0035] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0036] Furthermore, the acquisition, storage, use, and processing of data in this application's technical solution all comply with relevant national laws and regulations.

[0037] Figure 1 A schematic flowchart of a text-based robot response method according to an embodiment of this application is shown. Figure 1 As shown, in one embodiment of this application, a text robot response method is provided, applied to a client. The method includes the following steps:

[0038] S101: Generate query information based on the user's input operation, and send the query information to the text robot;

[0039] S102: If it is determined that the reply information received from the text robot is a customer information acquisition instruction, the customer information attribute is acquired, and the information acquisition method corresponding to the customer information attribute is determined;

[0040] S103: Obtain customer information according to the information acquisition method corresponding to the customer information attribute, generate customer information acquisition result, and send the customer information acquisition result to the text robot; wherein, the reply information is generated by the text robot based on the query information;

[0041] S104: Display the feedback information received from the text robot regarding the customer information acquisition results to the customer.

[0042] Specifically, in this embodiment, the user can query the text robot through a client, inputting information via the client. The client generates query information based on the user's input and sends it to the text robot. The text robot only needs to use its knowledge base to determine whether customer information needs to be obtained based on the query information, generate a response, and send the response to the client. No further modifications are needed to the text robot to obtain customer information. If the client determines that the response is a customer information retrieval instruction instructing the text robot to obtain customer information, it retrieves the customer information according to the instruction, generates a customer information retrieval result, and then feeds the result back to the text robot. The text robot, based on the customer information retrieval result and a pre-written script, assembles an answer, generates feedback information, sends the feedback information to the client, and displays the feedback information to the customer through the client.

[0043] The client can determine the attributes of customer information based on the customer information retrieval instruction, and then determine whether to retrieve the customer information through a local server or a network server based on these attributes. In this embodiment, a correspondence between customer information and its attributes can be established and stored in a correspondence table. The attributes of the customer information are determined by looking up the correspondence table. If the attribute is a local attribute, such as the customer's location information, the customer information can be retrieved through the local server; if the attribute is a network attribute, such as the customer's deposit information, the customer information can be retrieved through the network server.

[0044] In this embodiment, the client is installed on a mobile phone, computer, tablet or other electronic device. Those skilled in the art can set it according to the actual situation, and no restrictions are imposed in this embodiment.

[0045] According to the text robot response method provided in this application, it is possible to provide responses that are more in line with the actual situation of customers without modifying the text robot, thereby improving the accuracy of customer responses, narrowing the scope of modification, and reducing the investment cost of text robot response.

[0046] In one embodiment, the response information is generated by a text robot in the following manner: in response to a received query, semantic analysis is performed on the query to obtain a semantic analysis result; a response corresponding to the semantic analysis result is matched in a pre-configured knowledge base; the response information includes a customer information retrieval instruction and a display response.

[0047] Specifically, in this embodiment, after receiving an inquiry, the text robot performs semantic analysis on the inquiry to extract key elements that can be used for search and matching in the knowledge base, thus obtaining semantic analysis results. The knowledge base stores the correspondence between the question elements used by the text robot and the answer information, mainly entered by maintenance personnel. The text robot inputs the semantic analysis results into the knowledge base. If it does not need to retrieve customer information again, it generates and displays a response; if it needs to retrieve customer information again, it generates a customer information retrieval instruction as the response.

[0048] In one embodiment, the method further includes: if it is determined that the response information received from the text robot is display response information, directly displaying the display response information to the customer.

[0049] Specifically, in this embodiment of the application, if the text robot determines that it does not need customer information, it sends a display reply message to the client. After receiving the display reply message, the client displays the display reply message to the customer.

[0050] In one embodiment, the displayed response information is configured to be in text format.

[0051] In one embodiment, the customer information retrieval instruction and the customer information retrieval result are configured as identifiers.

[0052] Specifically, in this embodiment, if the text robot no longer needs to obtain customer information, it generates a text-based response and sends it to the client, which can then directly display the text information to the customer. If the text robot needs to obtain customer information again, it sends a customer information retrieval instruction in the corresponding identifier format. For example, "Q06000001" represents the customer information retrieval instruction for "querying nearby branches of the customer". After receiving the customer information retrieval instruction in the identifier format, the client parses the information in the "Q06000001" identifier format and retrieves the customer information according to the instruction. After retrieving the customer information, the client also generates a customer information retrieval result in the identifier format. If the customer information retrieval fails, the identifier "Q06000001_0001" is generated as the customer information retrieval result; if the customer information retrieval is successful, the identifier "Q06000001_0002" is generated and appended to the customer information retrieval result along with the customer information.

[0053] The identifiers in this application embodiment can be one or more combinations of symbols such as Chinese characters, English characters, numbers, punctuation marks, and mathematical operators. Those skilled in the art can choose according to the actual situation, and no restrictions are imposed in this embodiment.

[0054] According to the text robot response method provided in this application, it is possible to send and display reply information, customer information acquisition instructions and customer information acquisition results in different formats, so that the text robot and the client can directly determine whether customer information needs to be acquired and the specific content of the customer information acquisition results based on the information format. Moreover, sending in the identifier format can shorten the information recognition time of the text robot and the client and improve the information feedback efficiency.

[0055] In one embodiment, sending the customer information acquisition result to the text robot includes: if it is determined that the customer information acquisition result is successful, determining the attributes of the customer information carried in the customer information acquisition result; determining the encryption method of the customer information acquisition result based on the attributes of the customer information; encrypting the customer information acquisition result according to the determined encryption method; and sending the encrypted customer information acquisition result to the text robot.

[0056] Specifically, in this embodiment, if the customer has already granted permission to access customer information during a previous inquiry, the client can access the customer information during this inquiry. The attributes of the acquired customer information are then determined, and the encryption method is determined based on these attributes. If the customer information attributes are ordinary attributes, such as the customer's current location information or other information not involving customer privacy, then encryption of the acquired customer information is not required. If the customer information attributes are privacy attributes, such as the customer's deposit information or identity information, or other information involving customer privacy, then encryption of the acquired customer information is required. Furthermore, when the customer information attributes are also privacy attributes, corresponding encryption levels are further defined based on the privacy attributes. If the customer information attributes are first-class privacy information, such as the customer's deposit information or other information with a low level of protection, then the acquired customer information is encrypted using the encryption method of the first encryption level. If the customer information attributes are second-class privacy information, such as the customer's ID card or home address, or other information with a high level of protection, then the acquired customer information is encrypted using the encryption method of the second encryption level, which is higher than the first encryption level. In this embodiment, the encryption level and the attributes of the customer information can be set according to actual circumstances, and are not limited in this implementation.

[0057] The text robot response method provided in this application can encrypt the customer information acquisition results according to the attributes of the customer information, thereby protecting the customer's personal privacy and improving the security of information transmission.

[0058] In one embodiment, the feedback information is generated by the text robot in the following manner: if it is determined that the customer information acquisition result is successful, feedback information is assembled based on the customer information carried in the customer information acquisition result; if it is determined that the customer information acquisition result is unsuccessful, feedback information is generated to instruct the customer to grant the customer information acquisition permission.

[0059] Specifically, in this embodiment, if the text robot obtains customer information, it combines the obtained customer information with the script to assemble feedback information, which is then sent to the client. Upon receiving the feedback information, the client displays it and replies to the customer to answer their inquiry. If the customer did not grant permission to access customer information during a previous inquiry, the client cannot obtain customer information during this inquiry. The text robot, determining that customer information retrieval has failed, outputs a permission release prompt as feedback to the client. Upon receiving this feedback, the client displays it and replies to the customer to prompt them to grant permission to access customer information. After the customer grants permission, the client retrieves customer information again and generates a customer information retrieval result, which is then sent back to the text robot.

[0060] The text robot response method provided in this application can prompt the user to release the permission to obtain customer information when the user fails to obtain customer information, so as to facilitate the text robot to generate a more relevant response to the user's actual situation and improve the user experience.

[0061] Example 1

[0062] In this embodiment, an identifier command configuration is added to the knowledge base, using identifiers instead of ordinary text information. For example, "Q06000001" represents the command information "Query nearby service points for the customer". The identifier command information is similar to the ordinary robot text answer and can be entered by knowledge base maintenance personnel. After the text robot receives the query information forwarded by the client, it extracts the key information of the query information through semantic analysis and matches the most suitable answer in the knowledge base, which may match text format information or identifier format information.

[0063] If a text robot can generate response information without obtaining customer information, that is, it can match the text format of the response information in the knowledge base according to the semantic analysis results and send it to the client as the response information. The client will then display the response information to the customer to reply to the customer's inquiry.

[0064] If a text robot needs to retrieve customer information to generate a response, it matches a customer information retrieval instruction in an identifier format from the knowledge base based on semantic analysis results. This instruction is then sent to the client. The customer information retrieval instruction is pre-defined. Upon receiving the instruction, the client executes the pre-defined actions to retrieve the necessary customer information, generate a retrieval result, and sends it back to the text robot, preparing for its response.

[0065] The customer information retrieval result is also in identifier format. Taking "Query nearby branches" as an example, the client first retrieves the customer's current location based on the customer information retrieval instruction in the identifier format "Q06000001". If the client cannot retrieve the customer's location, it indicates that customer information retrieval has failed, and generates information in the identifier format "Q06000001_0001" as the customer information retrieval result. This result is then sent to a text robot. Upon receiving the result, the text robot matches it in its knowledge base to find the corresponding feedback information instructing the customer to grant permission to retrieve customer information. This feedback information is then sent to the client, which displays it to the customer, prompting them to grant permission. If the user grants permission, the client retrieves the customer information again.

[0066] In this embodiment, an intelligent AI algorithm is introduced on the client side to intelligently obtain other information related to customer information. If the client obtains the customer's current location and nearby service points, as well as service point information, it generates identifier information in the format "Q06000001_0002" and sends it along with the obtained information as the customer information retrieval result to the text robot. The text robot combines the obtained customer information retrieval result with the script to assemble and generate feedback information such as "The nearest service point to you is XXX, location XXX, phone number XXX, business hours XXXX", which is then pushed to the client as the answer and displayed to the customer.

[0067] Please refer to Figure 2 The second aspect of this application provides a text robot response method, applied to a text robot, comprising: S201: generating response information based on query information received from a client, and sending the response information to the client; wherein the query information is generated by the client based on user input; S202: generating feedback information based on customer information acquisition results received from the client, and sending the feedback information to the client for display to the customer; wherein, when the client determines that the response information is a customer information acquisition instruction, it acquires customer information attributes, determines the information acquisition method corresponding to the customer information attributes, acquires customer information according to the information acquisition method corresponding to the customer information attributes, and generates a customer information acquisition result.

[0068] In this embodiment of the application, generating response information based on the query information received from the client includes: responding to the received query information by performing semantic analysis on the query information to obtain a semantic analysis result; matching the response information corresponding to the semantic analysis result in a pre-configured knowledge base; the response information includes a customer information retrieval instruction and a display response information.

[0069] In this embodiment of the application, generating feedback information based on the customer information acquisition result received from the client includes: if the customer information acquisition result is determined to be successful, assembling feedback information according to the customer information carried in the customer information acquisition result; if the customer information acquisition result is determined to be unsuccessful, generating feedback information to instruct the customer to grant customer information acquisition permission.

[0070] It should be understood that although the steps in the flowchart above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart above may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0071] In one embodiment, such as Figure 3 As shown, a text robot response device 300 is provided, comprising:

[0072] Client 301 is configured to: generate and send query information based on user input; if the received response information is a customer information retrieval instruction, acquire customer information attributes and determine the information retrieval method corresponding to the customer information attributes; acquire customer information according to the information retrieval method corresponding to the customer information attributes, generate customer information retrieval results, and send customer information retrieval results; and display the received feedback information regarding the customer information retrieval results to the customer.

[0073] Text robot 302 is used to: generate response information based on received inquiry information and send the response information; generate feedback information based on received customer information acquisition results and send feedback information regarding the customer information acquisition results.

[0074] In one embodiment, generating response information based on received inquiry information includes: performing semantic analysis on the inquiry information to obtain a semantic analysis result; matching the response information corresponding to the semantic analysis result in a pre-configured knowledge base; the response information includes a customer information retrieval instruction and a display response information.

[0075] In one embodiment, sending the customer information acquisition result includes: if the customer information acquisition result is determined to be a successful acquisition of customer information, determining the attributes of the customer information carried in the customer information acquisition result; determining the encryption method of the customer information acquisition result based on the attributes of the customer information; encrypting the customer information acquisition result according to the determined encryption method; and sending the encrypted customer information acquisition result.

[0076] In one embodiment, generating feedback information based on the received customer information acquisition result includes: if the customer information acquisition result is determined to be successful, assembling feedback information based on the customer information carried in the customer information acquisition result; and if the customer information acquisition result is determined to be unsuccessful, generating feedback information to instruct the customer to grant customer information acquisition permission.

[0077] The text robot response device includes a processor and a memory. The client and the text robot are stored in the memory as program units, and the processor executes the program modules stored in the memory to implement the corresponding functions.

[0078] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and the text-based robot response method can be implemented by adjusting the kernel parameters.

[0079] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0080] This application provides a processor configured to execute the text robot response method applied to a client as described above, or configured to execute the text robot response method applied to a text robot as described above.

[0081] This application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the text robot response method applied to a client as described above, or to perform the text robot response method applied to a text robot as described above.

[0082] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. Figure 4This schematic diagram illustrates the internal structure of a computer device according to an embodiment of the present application. The computer device includes a processor A01, a network interface A02, a memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The network interface A02 is used for communication with external terminals via a network connection. When the computer program B02 is executed by the processor A01, it implements a text-based robot response method.

[0083] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0084] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program with the following method steps: generating query information based on user input and sending the query information to a text robot; if the response information received from the text robot is a customer information retrieval instruction, acquiring customer information attributes and determining the information retrieval method corresponding to the customer information attributes; acquiring customer information according to the information retrieval method corresponding to the customer information attributes, generating a customer information retrieval result, and sending the customer information retrieval result to the text robot; wherein, the response information is generated by the text robot based on the query information; and displaying the feedback information received from the text robot regarding the customer information retrieval result to the customer.

[0085] In one embodiment, the response information is generated by a text robot in the following manner: in response to a received query, semantic analysis is performed on the query to obtain a semantic analysis result; a response corresponding to the semantic analysis result is matched in a pre-configured knowledge base; the response information includes a customer information retrieval instruction and a display response.

[0086] In one embodiment, the method further includes: if it is determined that the response information received from the text robot is display response information, directly displaying the display response information to the customer.

[0087] In one embodiment, the displayed response information is configured to be in text format.

[0088] In one embodiment, the customer information retrieval instruction and the customer information retrieval result are configured as identifiers.

[0089] In one embodiment, sending the customer information acquisition result to the text robot includes: if it is determined that the customer information acquisition result is successful, determining the attributes of the customer information carried in the customer information acquisition result; determining the encryption method of the customer information acquisition result based on the attributes of the customer information; encrypting the customer information acquisition result according to the determined encryption method; and sending the encrypted customer information acquisition result to the text robot.

[0090] In one embodiment, the feedback information is generated by the text robot in the following manner: if it is determined that the customer information acquisition result is successful, feedback information is assembled based on the customer information carried in the customer information acquisition result; if it is determined that the customer information acquisition result is unsuccessful, feedback information is generated to instruct the customer to grant the customer information acquisition permission.

[0091] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0093] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0095] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0096] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0097] Computer-readable media include both permanent and non-permanent, removable and non-removable media, which can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0099] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A text-based robot response method, characterized in that, Applied to the client, the text robot response method includes: Generate query information based on user input and send the query information to the text robot; If the response received from the text robot is determined to be a pre-agreed customer information retrieval instruction, the customer information attributes are obtained, and the information retrieval method corresponding to the customer information attributes is determined; wherein, the customer information attributes include local attributes and network attributes, and the information retrieval method includes retrieving customer information through a local server and retrieving customer information through a network server; According to the customer information acquisition instruction, the pre-agreed actions are executed, customer information is acquired according to the information acquisition method corresponding to the customer information attribute, customer information acquisition result is generated, and customer information acquisition result is sent to the text robot; wherein, the reply information is generated by the text robot based on the query information; The feedback information received from the text robot regarding the customer information acquisition results will be displayed to the customer.

2. The text robot response method according to claim 1, characterized in that, The response information was generated by the text robot using the following method: In response to the received query information, semantic analysis is performed on the query information to obtain the semantic analysis result; Match the response information corresponding to the semantic analysis results in a pre-configured knowledge base; The response information includes instructions for obtaining customer information and the displayed response information.

3. The text robot response method according to claim 2, characterized in that, The method further includes: If the response received from the text robot is determined to be a display response, the display response is directly shown to the customer.

4. The text robot response method according to claim 2, characterized in that, The displayed response information is configured to be in text format.

5. The text robot response method according to claim 1, characterized in that, The customer information retrieval instruction and the customer information retrieval result are configured as identifiers.

6. The text robot response method according to claim 1, characterized in that, Sending the customer information acquisition results to the text robot includes: If the customer information retrieval result is determined to be successful, the attributes of the customer information carried in the customer information retrieval result shall be determined. The encryption method for obtaining customer information is determined based on the attributes of the customer information. The obtained customer information is encrypted according to the determined encryption method; Send the encrypted customer information retrieval results to the text robot.

7. The text robot response method according to claim 1, characterized in that, The feedback information is generated by the text robot in the following way: If the customer information acquisition result is determined to be successful, feedback information is assembled based on the customer information carried in the customer information acquisition result. If the customer information retrieval result is determined to be a failure, a feedback message is generated to instruct the customer to grant permission to retrieve customer information.

8. A text-based robot response method, characterized in that, Applied to text-based robots, the text-based robot response method includes: Based on the query information received from the client, a response is generated and sent to the client; wherein the query information is generated by the client based on the user's input. Based on the customer information retrieval result received from the client, feedback information is generated and sent to the client for display to the customer. The customer information retrieval result is generated by the client executing a pre-agreed action according to a customer information retrieval instruction, retrieving customer information according to the information retrieval method corresponding to the customer information attributes. The customer information attributes include local attributes and network attributes, and the information retrieval methods include retrieving customer information through a local server and retrieving customer information through a network server. The customer information attributes and the corresponding information retrieval methods are obtained and determined by the client when it is determined that the response information is a pre-agreed customer information retrieval instruction.

9. The text robot response method according to claim 8, characterized in that, The process of generating response information based on the query information received from the client includes: In response to the received query information, semantic analysis is performed on the query information to obtain the semantic analysis result; Match the response information corresponding to the semantic analysis result in a pre-configured knowledge base; the response information includes customer information retrieval instructions and display response information.

10. The text robot response method according to claim 9, characterized in that, The step of generating feedback information based on the customer information received from the client includes: If the customer information acquisition result is determined to be successful, feedback information is assembled based on the customer information carried in the customer information acquisition result. If the customer information retrieval result is determined to be a failure, a feedback message is generated to instruct the customer to grant permission to retrieve customer information.

11. A text robot response device, characterized in that, The text robot response device includes: Client, used for: Generate and send query information based on user input; If the received response information is determined to be a pre-agreed customer information retrieval instruction, the customer information attributes are obtained, and the information retrieval method corresponding to the customer information attributes is determined; wherein, the customer information attributes include local attributes and network attributes, and the information retrieval method includes retrieving customer information through a local server and retrieving customer information through a network server; According to the customer information acquisition instruction, execute the pre-agreed action, acquire customer information according to the information acquisition method corresponding to the customer information attribute, generate customer information acquisition result, and send the customer information acquisition result; Display the feedback information received regarding the customer information acquisition results to the customer; Text bots, used for: Generate a response based on the received query information and send the response. Based on the received customer information, generate feedback information and send feedback information regarding the customer information acquisition results.

12. The text robot response device according to claim 11, characterized in that, The step of generating response information based on the received query information includes: Perform semantic analysis on the query information to obtain the semantic analysis results; Match the response information corresponding to the semantic analysis result in a pre-configured knowledge base; the response information includes customer information retrieval instructions and display response information.

13. The text robot response device according to claim 11, characterized in that, The result of sending customer information includes: If the customer information retrieval result is determined to be successful, the attributes of the customer information carried in the customer information retrieval result shall be determined. The encryption method for obtaining customer information is determined based on the attributes of the customer information. The obtained customer information is encrypted according to the determined encryption method; Send encrypted customer information to obtain results.

14. The text robot response device according to claim 11, characterized in that, The step of generating feedback information based on the received customer information includes: If the customer information acquisition result is determined to be successful, feedback information is assembled based on the customer information carried in the customer information acquisition result. If the customer information retrieval result is determined to be a failure, a feedback message is generated to instruct the customer to grant permission to retrieve customer information.

15. A processor, characterized in that, It is configured to perform the text robot response method according to any one of claims 1 to 7, or to perform the text robot response method according to any one of claims 8 to 10.

16. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, the instruction causes the processor to be configured to perform the text robot response method of any one of claims 1 to 7, or to perform the text robot response method of any one of claims 8 to 10.

17. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the text robot response method of any one of claims 1 to 7, or the text robot response method of any one of claims 8 to 10.

Images