Data processing method and apparatus

Abstract

The application provides a data processing method and device, wherein the data processing method comprises the following steps: receiving a natural language question sentence for a target service; processing the natural language question sentence based on a third-party language analysis tool to obtain service credential data, wherein the service credential data is determined in a preset service through a credential query link; and according to the service credential data, the target service data corresponding to the service credential data is determined by querying in the preset service through a data query link. Through the convenience of the third-party language analysis tool in actual application, the professional threshold of data inquirers is reduced, and at the same time, the target service data cannot be sent to the third-party developer, so that the data security of users is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a data processing method. The present application also relates to a data processing device, a computing device and a computer readable storage medium. BACKGROUND

[0002] With the development of computer technology, artificial intelligence has also developed rapidly. When a user performs data query, the user can perform query with the aid of an API (Application Programming Interface) of natural language processing. For example, the user only needs to input the content to be queried in natural language through the API interface, and the API interface can feed back relevant information to the user.

[0003] However, in general, the API of natural language processing is a tool developed by a third party. When the user wants to query some sensitive information, if the API interface is used, there is a risk of information leakage, that is, the personal information of the user is leaked to the third-party developer of the API. Therefore, how to use the third-party natural language processing API which is convenient and fast and ensure the data security of the user is a problem to be solved by technical personnel at present. SUMMARY

[0004] Therefore, the embodiments of the present application provide a data processing method. The present application also relates to a data processing device, a computing device and a computer readable storage medium to solve the above problems in the prior art.

[0005] According to a first aspect of the embodiments of the present application, a data processing method is provided, comprising:

[0006] receiving a natural language question sentence for a target service;

[0007] processing the natural language question sentence based on a third-party language analysis tool to obtain service credential data, wherein the service credential data is determined in a preset service through a credential query link;

[0008] According to the service credential data, the target service data corresponding to the service credential data is determined by querying in the preset service through a data query link.

[0009] According to a second aspect of the embodiments of the present application, a data processing device is provided, comprising:

[0010] The receiving module is configured to receive a natural language question sentence for a target service;

[0011] The acquisition module is configured to acquire business credential data based on the third-party language analysis tool processing the natural language question, wherein the business credential data is determined in the preset business service through a credential query link.

[0012] The determination module is configured to determine target business data corresponding to the business credential data by querying in the preset business service through a data query link according to the business credential data.

[0013] According to a third aspect of an embodiment of the present application, a computing device is provided, comprising a memory, a processor, and computer instructions stored in the memory and executable on the processor, wherein the processor executes the computer instructions to implement the steps of the data processing method.

[0014] According to a fourth aspect of an embodiment of the present application, a computer readable storage medium is provided, which stores computer instructions executable by a processor to implement the steps of the data processing method.

[0015] The data processing method provided by the present application receives a natural language question for a target business; acquires business credential data based on a third-party language analysis tool processing the natural language question, wherein the business credential data is determined in a preset business service through a credential query link; and determines target business data corresponding to the business credential data by querying in the preset business service through a data query link according to the business credential data.

[0016] An embodiment of the present application realizes that after receiving a natural language question for a target business, the natural language question is processed by a third-party language analysis tool, target business data is acquired in a preset business service, the business credential data corresponding to the target business data is one-to-one, the third-party language analysis tool acquires business credential data representing the target business data, rather than the target business data itself, and finally the real target business data is acquired in the business service based on the business credential data through another communication connection. Through the method provided by the present application, the convenience of the third-party language analysis tool in actual application can be fully utilized, the professional threshold of data inquirers is reduced, users can directly make corresponding inquiries according to natural language without learning corresponding inquiry languages, and the target business data is ensured not to be sent to a third-party developer, thereby ensuring the data security of users. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is an architecture diagram of a data processing system provided by an embodiment of the present application;

[0018] Figure 2is a flowchart of a data processing method provided by an embodiment of the present application;

[0019] Figure 3 is a processing flowchart of a data processing method applied to a resource account information query scenario provided by an embodiment of the present application;

[0020] Figure 4 is a structural schematic diagram of a data processing apparatus provided by an embodiment of the present application;

[0021] Figure 5 is a structural block diagram of a computing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0022] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced without the specific details, and it is understood that the present application is not limited to the embodiments described herein. In other instances, well-known methods, procedures, components, and circuits have not been described in detail as not to unnecessarily obscure aspects of the present application.

[0023] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of one or more embodiments of the present application. As used in one or more embodiments of the present application and the accompanying claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in one or more embodiments of the present application and the following claims, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0024] It is to be understood that the terms first, second, etc. can be employed in this disclosure to describe various information. Such information should not be limited by these terms. These terms are only used to distinguish one category of information from another. For example, without departing from the scope of one or more embodiments of the present application, first can be termed second, and similarly, second can be termed first. Depending on the context, the word "if' as used herein can be interpreted to mean "when" or "in response to determining." Depending on the context, the word "if' as used herein can be interpreted to mean "when" or "in response to determining."

[0025] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards in relevant regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0026] With the development of computer technology, artificial intelligence has also developed rapidly. When a user performs data query, the user can perform query with the assistance of an API (Application Programming Interface) of natural language processing. For example, the user only needs to input the content to be queried in natural language through the API interface, and the API interface can feed back relevant information to the user.

[0027] However, generally, the API of natural language processing is a tool developed by a third party. When the user wants to query some sensitive information, if the API interface is used, there is a risk of information leakage, that is, the personal information of the user is leaked to the third-party developer of the API. In the current processing method, some technologies encrypt the business data to be queried when the business data is queried by using the API interface of natural language, and then return the encrypted business data to the user, and the user decrypts again. Although this method can solve the problem of information security to a certain extent, the essence of encrypting the business data is still to encrypt on the basis of the original business data, and send the encrypted business data to the third-party API. In this way, the third-party developer can still get the encrypted business data, and in this case, there is still a risk of business data leakage.

[0028] Based on this, in the present application, a data processing method is provided, and the present application also relates to a data processing device, a computing device, and a computer readable storage medium, which are described in detail one by one in the following embodiments.

[0029] Reference Figure 1 , Figure 1 An architecture diagram of a data processing system provided by an embodiment of the present application is shown, and the data processing system can include a client 100 and a server 200.

[0030] The client 100 is configured to send a natural language question sentence for a target business to the server 200.

[0031] The server 200 is configured to process the natural language question sentence based on a third-party language analysis tool to obtain business credential data, wherein the business credential data is determined in a preset business service through a credential query link; according to the business credential data, the target business data corresponding to the business credential data is determined by querying in the preset business service through a data query link; and the target business data is sent to the client 100.

[0032] The client 100 is further configured to receive the target business data sent by the server 200.

[0033] The data processing system can include a plurality of clients 100 and a server 200, where the client 100 can be referred to as an end-side device, and the server 200 can be referred to as a cloud-side device. The plurality of clients 100 can establish a communication connection through the server 200. In a data query scenario, the server 200 is used to provide data query services between the plurality of clients 100. The plurality of clients 100 can respectively act as a sending end or a receiving end to implement communication through the server 200.

[0034] A user can interact with the server 200 through the client 100 to receive data sent by other clients 100 or send data to other clients 100, and the like. In a data query scenario, the user can publish a data stream to the server 200 through the client 100. The server 200 generates target business data according to the data stream and pushes the target business data to other clients that establish a communication connection.

[0035] The client 100 and the server 200 establish a connection through a network. The network provides a medium for a communication link between the client 100 and the server 200. The network can include various connection types, such as wired, wireless communication links, or optical fiber cables, and the like. The data transmitted by the client 100 can need to be processed through encoding, transcoding, compression, and the like before being published to the server 200.

[0036] The client 100 can be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5) application, or a light application (also referred to as a small program, a lightweight application program), or a cloud application, and the like. The client 100 can be developed based on a software development kit (SDK) provided by the server 200 for a corresponding service, such as an RTC (Real Time Communication) SDK. The client 100 can be deployed in an electronic device and needs to depend on the device or some APP in the device to run, and the like. The electronic device can have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, and the like. Various other types of applications can also be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant communication tools, mailbox clients, social platform software, and the like.

[0037] The service end 200 can include a server providing various services, for example, a server providing a communication service for a plurality of clients, for example, a server for background training supporting a model used on a client, for example, a server processing data sent by a client, and the like. It should be noted that the service end 200 can be implemented as a distributed server cluster composed of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server of a cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN, Content Delivery Network), and big data and artificial intelligence platforms, and the like. Basic cloud computing services of the cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0038] It should be noted that the data processing method provided in the embodiments of the present application is generally executed by the service end, but in other embodiments of the present application, the client can also have similar functions as the service end, so as to execute the data processing method provided in the embodiments of the present application. In other embodiments, the data processing method provided in the embodiments of the present application can also be executed by the client and the service end together.

[0039] Figure 2 A flowchart of a data processing method according to an embodiment of the present application is shown, which specifically includes the following steps:

[0040] Step 202: receiving a natural language question sentence for a target service.

[0041] In actual applications, the method provided in the present application can receive the natural language question sentence sent by the user for the target service through the service end, or through the client. In one or more embodiments of the present application, a data query method is provided, and the user can quickly and conveniently process the natural language question sentence by using a third-party natural language processing tool, and the information security of the user can be protected.

[0042] Specifically, the target service specifically refers to a related service to which the natural language question sentence sent by the user is directed. The natural language question sentence specifically refers to a sentence composed of a natural language evolving with culture, for example, a Chinese sentence, an English sentence, a French sentence, and the like.

[0043] For example, the user wants to consult the related information of A service, and can send a Chinese sentence for A service. For another example, the user wants to consult the related information of B service, and can send an English sentence for B service, and the like.

[0044] In an embodiment provided by the present application, the method of the present application provides a data query system which provides a user with an asset information query service under a certain asset account. When the user wants to query his own asset information, the user can send a natural language question "How much balance do I have under the A asset account?".

[0045] In an embodiment provided by the present application, the natural language question for the target service is received, including:

[0046] Based on the calling request of the user, a user interface is displayed for the user;

[0047] The natural language question for the target service input by the user based on the user interface is received.

[0048] In actual application, the method provided by the present application aims to facilitate the operation and use of the user. Further, the corresponding user interface can be displayed for the user according to the calling request of the user, so as to facilitate the user to perform corresponding operations in the user interface.

[0049] The calling request specifically refers to a request for calling the data query system. For example, the user clicks a start button, and the calling request of the data query system is triggered by the operation of clicking the start button. The server displays the corresponding user interface for the user based on the calling request. The user interface can be understood as a front-end display interface of the data query system. The user can perform interface operations such as input, click, and slide in the user interface.

[0050] After the user interface is displayed to the user, the user can input the natural language question for the target service in the user interface. Further, the natural language question can be in the form of text or in the form of voice, which is not limited in the present application.

[0051] In an embodiment provided by the present application, the user inputs the corresponding natural language question in the text box of the user interface.

[0052] In another embodiment provided by the present application, the user selects voice input in the input mode switching tool of the user interface, calls a microphone device to collect voice information of the user, and determines the natural language question input by the user from the voice information.

[0053] In actual application, the personal information of each user is protected, and the user cannot obtain the information of other users, and the information of the user himself cannot be obtained by other users. Based on this, in an embodiment provided by the present application, the method further includes:

[0054] The username and password of the user are received.

[0055] The user's identity information is verified based on the username and password.

[0056] The user's username and password are used to verify the user's identity information in the data query system. Users can pre-register their username and corresponding password. This serves two purposes: firstly, it facilitates the verification of the user's identity information and ensures the security of the user's data; secondly, it makes it easier and faster to find the relevant business data corresponding to the username in subsequent business processing.

[0057] After receiving the user's username and password, the system must then verify the user's identity information based on these credentials. Specifically, this verification process determines whether the user's identity verification is successful or failed. In particular, if the username and password match pre-saved username and password, the user's identity verification is successful; otherwise, the verification fails.

[0058] Step 204: Process the natural language question using a third-party language parsing tool to obtain business credential data, wherein the business credential data is determined in a preset business service through a credential query link.

[0059] Third-party language parsing tools specifically refer to natural language processing tools released by third parties. These tools, such as intelligent chatbots, can engage in conversation by understanding and learning human language. They can also interact based on the context of the chat, communicate like humans, and complete some relatively complex tasks.

[0060] The development of third-party language parsing tools is quite rapid, providing greater convenience for users' lives and work. However, while these tools offer convenience, they also raise information security concerns. Therefore, balancing the relationship between third-party language parsing tools and the security of users' personal information has become a key research focus.

[0061] In the method provided in this application, users can use third-party language parsing tools to process natural language questions. However, when the third-party language parsing tool accesses business data, it is not allowed to directly access the actual business data of the business service. Instead, the business credential data corresponding to the business data is sent to the third-party language parsing tool.

[0062] The business credential data is a value corresponding to the business data, and the business credential data and the business data can be understood as a key-value pair. Only the credential issuing party knows what the business credential data represents, and no other method can obtain the original business data.

[0063] The difference between the business credential data and the business encryption data is that the business encryption data is generated by encrypting the original business data, and the original business data can be restored from the business encryption data after obtaining the business encryption data. The business credential data only represents the identifier of the original business data, and after obtaining the business credential data, no one can obtain the original business data according to the business credential data except the party issuing the business credential data.

[0064] In the method provided in the application, the third-party language analysis tool establishes a credential query link with a preset business service, wherein the preset business service specifically refers to a service provided for a target business, and the credential query link specifically refers to a communication connection between the third-party language analysis tool and the preset business service. The credential query link is used for the preset business service to send business credential data to the third-party language analysis tool.

[0065] The business credential data is generated by the preset business service after querying the corresponding target business data after receiving the calling request sent by the third-party language analysis tool, and the preset business service sends the business credential data corresponding to the target business data to the third-party language analysis tool through the credential query link after obtaining the target business data, thereby ensuring the data security of the target business data.

[0066] Based on the third-party language analysis tool processing the natural language question, the business credential data is obtained, wherein the business credential data is determined in the preset business service through the credential query link.

[0067] In a specific embodiment provided in the application, based on the third-party language analysis tool processing the natural language question, the business credential data is obtained, including:

[0068] Establishing a credential query link between the preset business service and the third-party language analysis tool;

[0069] Based on the credential query link, receiving a business query request generated by the third-party language analysis tool based on the natural language question;

[0070] In response to the business query request, the business credential data is sent to the third-party language analysis tool through the credential query link.

[0071] Specifically, when the user inputs the natural language question, the natural language question is transmitted to the third-party language analysis tool through the input interface corresponding to the third-party language analysis tool, and a credential query link between the third-party language analysis tool and the preset business service is established.

[0072] Through the credential query link, a business query request generated by the third-party language analysis tool based on the natural language question is received. In the method provided in the present application, the specific operation in the third-party language analysis tool is not limited, and the actual application is used as the criterion.

[0073] The business query request specifically refers to a business query request extracted from the natural language question by the third-party language analysis tool based on the processing capability of the third-party language analysis tool after receiving the natural language question. After receiving the business query request, corresponding business credential data can be obtained in the preset business service in response to the business query request, and finally the business credential query data is sent to the third-party language analysis tool through the credential query link.

[0074] Specifically, in response to the business query request, the business credential data is sent to the third-party language analysis tool through the credential query link, which includes:

[0075] At least one business interface call request is generated in response to the business query request.

[0076] The target business data corresponding to the business query request is determined based on each business interface call request.

[0077] The target business data corresponding to the business query request is determined based on each business interface call request.

[0078] In actual application, there is one or more business interfaces in the preset business service, each business interface provides different services, when a business query request is received, the business query request may need at least one business interface to cooperate, obtain target business data, and generate corresponding business credential data based on the target business data.

[0079] After obtaining the business query request, at least one business interface corresponding to the business query request is determined, and the business interface call request corresponding to each business interface is generated respectively. Through each business interface call request, the preset business service can be executed, so as to obtain the target business data corresponding to the business query request.

[0080] After obtaining the target service data, the target service data cannot be directly sent to the third-party language analysis tool, but the service credential data corresponding to the target service data needs to be generated, and then the service credential is sent to the third-party language analysis tool through the credential query link.

[0081] There are many ways to generate the service credential data corresponding to the target service data, for example, a credential table is pre-configured, and the service credential data corresponding to each service data is determined in the credential table. For example, according to the random generation principle, a service credential data is randomly generated for the target service data after determining the target service data. In the method provided in the present application, the specific way of generating the service credential data from the target service data is not limited, and the actual application is used as the criterion.

[0082] Further, based on each service interface call request, the target service data corresponding to the service query request is determined, comprising:

[0083] The calling sequence of each service interface call request is determined.

[0084] Based on the calling sequence, the service interface corresponding to each service interface call request is called in sequence to communicate with the preset service, and the target service data is obtained.

[0085] In actual application, in the process of determining the target service data according to each service interface call request, the calling sequence of each service interface call request is determined first, and then each service interface is called based on the calling sequence, so as to obtain the final target service data.

[0086] Specifically, in the process of obtaining the final target service data by the service query request, the cooperation of one or more service interface call requests is needed, and the tasks handled by each service interface are different. The input parameter of some service interface is the output parameter of another service interface. Therefore, after determining each service interface request, the calling sequence of each service interface call request is determined, and the service interface is called based on the calling sequence.

[0087] In a specific embodiment provided in the present application, taking the received service query request Q as an example, the service query request Q needs to call the service interface 1, the service interface 2, the service interface 3 and the service interface 4. Therefore, the service interface call request Q1, the service interface call request Q2, the service interface call request Q3 and the service interface call request Q4 are generated. The calling sequence of each service interface call request is determined as "Q2, Q4, Q1, Q3". Based on the calling sequence, the service interface 2, the service interface 4, the service interface 1 and the service interface 3 are called in sequence, so as to obtain the final target service data.

[0088] The target business data corresponding to the business credential data is generated, and the business credential data is returned to the front end through a third-party language analysis tool.

[0089] In step 206, according to the business credential data, the target business data corresponding to the business credential data is determined by querying in the preset business service through a data query link.

[0090] After obtaining the business credential data from the third-party language analysis tool, a data query link between the front end and the preset business service is established. The business credential data is sent to the preset business service through the data query link, and the corresponding target business data is obtained through the business credential data.

[0091] It should be noted that in the process of obtaining the target business data through the business credential data, the data query link different from the credential query link is used for querying, so as to avoid that the third-party language analysis tool obtains the target business data.

[0092] In a specific embodiment provided in the present application, according to the business credential data, the target business data corresponding to the business credential data is determined by querying in the preset business service through a data query link, including:

[0093] In the case that the user identity information is verified, according to the business credential data, the target business data corresponding to the business credential data is determined by querying in the preset business service through a data query link.

[0094] In actual application, before querying the target business data according to the business credential data, the user identity information of the user is further confirmed, and only when the user identity information of the user is verified, the operation of querying the target business data according to the business credential data through the data query link is executed.

[0095] Further, the login duration of the user in the case that the user identity information is verified after logging into the data query system can be counted, and when the login duration is less than or equal to the preset login duration, it is determined that the user identity information is verified. The username and password can also be verified again before the business credential data is sent to the preset business service, and then the user identity information is determined.

[0096] In another specific embodiment provided in the present application, the method further includes:

[0097] In the case that the business credential data meets the credential deletion condition, the business credential data is deleted.

[0098] Specifically, the credential deletion condition includes:

[0099] The number of uses of the service credential data is greater than or equal to a preset number threshold; and / or,

[0100] The credential generation duration of the service credential data is greater than or equal to a preset duration threshold.

[0101] In actual application, the service credential data can be deleted according to actual conditions, and in the case of ensuring data security, the resources occupied by the service credential data can be further reduced. When the service credential data meets the credential deletion condition, the service credential data can be deleted, and if the service credential data is needed again, new service credential data can be generated according to actual conditions.

[0102] Further, the credential deletion condition has many, which can be set according to actual conditions, for example, the number of uses of the service credential data is less than or equal to a preset number threshold, for example, a certain service credential data can be used only once, after the service credential data is generated and the query operation is performed once, the service credential data will be deleted.

[0103] For example, the credential deletion condition can also be determined according to the credential generation duration, for example, the use duration of a certain service credential data is 5 minutes, which is calculated from the time point of generating the service credential data, and the service credential data can be used multiple times to query the target service data within 5 minutes. After 5 minutes, the service credential data is deleted.

[0104] For example, the credential deletion condition can also be determined according to the number of uses and the credential generation duration, for example, it is stipulated that the service credential data can be used 2 times within 5 minutes, when the credential generation duration of the service credential data exceeds 5 minutes, or the number of uses of the service credential data meets 2 times, the service credential data is deleted.

[0105] An embodiment of the present application realizes that after receiving the natural language question sentence for the target service, the natural language question sentence is processed by the third-party language analysis tool, the target service data corresponding to the service credential data is obtained in the preset service, the service credential data is one-to-one corresponding to the target service data, the third-party language analysis tool obtains the service credential data representing the target service data, rather than the target service data itself, and finally the real target service data is obtained in the service based on the service credential data through another communication connection. Through the method provided by the present application, the convenience of the third-party language analysis tool in actual application can be fully utilized, the professional threshold of the data inquirer is reduced, the user can directly query according to the natural language, without learning the corresponding query language, and at the same time, the target service data can be ensured not to be sent to the third-party developer, and the data security of the user is ensured.

[0106] The following is described in conjunction with the accompanyingFigure 3 With the application of the data processing method provided in the present application in the resource account information query scenario as an example, the data processing method is further described. Among them, Figure 3 A processing flowchart of a data processing method applied to a resource account information query scenario provided by an embodiment of the present application is shown, which specifically includes the following steps:

[0107] Step 302: Based on the user's call request, a user interface is displayed for the user.

[0108] Step 304: Receive the user's username and user password, and verify the user's user identity information based on the username and user password.

[0109] Step 306: In the case where the user identity information is verified, receive the natural language question sentence input by the user based on the user interface for the resource account.

[0110] Step 308: Establish a credential query link with a third-party language analysis tool.

[0111] Step 310: Based on the credential query link, receive the resource query request generated by the third-party language analysis tool based on the natural language question sentence.

[0112] Step 312: Generate at least one resource query interface call request in response to the resource query request.

[0113] Step 314: Determine the call order of each resource query interface call request, and based on the call order, sequentially call the resource query interface corresponding to each resource query interface call request to communicate with the preset resource service, and obtain the target resource data.

[0114] Step 316: Generate resource credential data corresponding to the target resource data, and send the resource credential data to the third-party language analysis tool through the credential query link.

[0115] Step 318: In the case where the user identity information is verified, according to the resource credential data, through the data query link in the preset resource service, determine the target resource data corresponding to the resource credential data.

[0116] Step 320: Display the target resource data in the user interface.

[0117] An embodiment of the present application realizes that after receiving a natural language question sentence for a target service, the natural language question sentence is processed by a third-party language analysis tool, target service data corresponding to service credential data is obtained in a preset service, the service credential data and the target service data are one-to-one corresponding, the third-party language analysis tool obtains the service credential data representing the target service data, rather than the target service data itself, and finally the real target service data is obtained in the service based on the service credential data through another communication connection. Through the method provided by the present application, the convenience of the third-party language analysis tool in actual application can be fully utilized, the professional threshold of data inquirers is reduced, users can directly query according to the natural language, without learning the corresponding query language, and meanwhile, the target service data can be ensured not to be sent to the third-party developer, so that the data security of the user is ensured.

[0118] Corresponding to the method embodiments described above, the present application also provides data processing device embodiments, Figure 4 The structure of a data processing device provided by an embodiment of the present application is shown. As shown in the figure, Figure 4 The device comprises:

[0119] The receiving module 402 is configured to receive a natural language question sentence for a target service;

[0120] The obtaining module 404 is configured to process the natural language question sentence based on a third-party language analysis tool to obtain service credential data, wherein the service credential data is determined in a preset service through a credential query link;

[0121] The determining module 406 is configured to query the target service data corresponding to the service credential data in the preset service through a data query link according to the service credential data.

[0122] Optionally, the obtaining module 404 is further configured to:

[0123] Establish a credential query link between the preset service and the third-party language analysis tool;

[0124] Based on the credential query link, receive a service query request generated by the third-party language analysis tool based on the natural language question sentence;

[0125] In response to the service query request, send the service credential data to the third-party language analysis tool through the credential query link.

[0126] Optionally, the obtaining module 404 is further configured to:

[0127] generating at least one business interface calling request in response to the business query request;

[0128] determining target business data corresponding to the business query request based on each business interface calling request;

[0129] generating business credential data corresponding to the target business data, and sending the business credential data to the third-party language analysis tool through the credential query link.

[0130] Optionally, the apparatus further comprises:

[0131] a deletion module configured to delete the business credential data if the business credential data meets a credential deletion condition.

[0132] Optionally, the credential deletion condition comprises:

[0133] a usage frequency of the business credential data is greater than or equal to a preset frequency threshold; and / or,

[0134] a credential generation duration of the business credential data is greater than or equal to a preset duration threshold.

[0135] Optionally, the obtaining module 404 is further configured to:

[0136] determine a calling order of each business interface calling request;

[0137] based on the calling order, sequentially call a business interface corresponding to each business interface calling request to communicate with the preset business service to obtain the target business data.

[0138] Optionally, the receiving module 402 is further configured to:

[0139] based on the calling request of the user, display a user use interface to the user;

[0140] receive a natural language question sentence for a target business input by the user based on the user use interface.

[0141] Optionally, the apparatus further comprises:

[0142] a verification module configured to receive a user name and a user password of the user, and verify user identity information of the user based on the user name and the user password;

[0143] Correspondingly, the determining module 406 is further configured to:

[0144] if the user identity information is verified, determine target business data corresponding to the business credential data by querying in the preset business service through a data query link according to the business credential data.

[0145] An embodiment of the present application realizes that after receiving a natural language question sentence for a target service, the natural language question sentence is processed by a third-party language analysis tool, target service data corresponding business credential data is obtained in a preset business service, the business credential data and the target service data are one-to-one corresponding, the third-party language analysis tool obtains the business credential data representing the target service data, rather than the target service data itself, and finally the real target service data is obtained in the business service based on the business credential data through another communication connection. Through the device provided by the present application, the convenience of the third-party language analysis tool in actual application can be fully utilized, the professional threshold of data inquirers is reduced, users can directly query according to natural language, without learning the corresponding query language, and the target service data can be ensured not to be sent to the third-party developer, thereby ensuring the data security of the user.

[0146] The above is a schematic scheme of the data processing device of the embodiment. It should be noted that the technical scheme of the data processing device and the technical scheme of the data processing method described above belong to the same concept, and the details of the technical scheme of the data processing device which are not described in detail can be referred to the description of the technical scheme of the data processing method.

[0147] Figure 5 A structural block diagram of a computing device 500 according to an embodiment of the present application is shown. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 through a bus 530, and a database 550 is used to save data.

[0148] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or combinations of such networks, such as the Internet. The access device 540 can include one or more of any type of network interface (for example, a network interface card (NIC)), such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, or the like.

[0149] In one embodiment of the present application, the above-described components of the computing device 500, as well as other components not shown in FIG. 5, can be connected to each other by a bus. It should be understood that Figure 5 Figure 5 The computing device structure diagram shown is merely for the purpose of example, and is not a limitation on the scope of the present application. Other components can be added or replaced by those skilled in the art as needed.

[0150] The computing device 500 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (for example, a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, or the like), a mobile phone (for example, a smartphone), a wearable computing device (for example, a smartwatch, smartglasses, or the like), or other type of mobile device, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 500 can also be a mobile or stationary server.

[0151] The processor 520 executes the computer instructions to implement the steps of the data processing method.

[0152] ​The above is a schematic scheme of the computing device of the embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the data processing method described above belong to the same concept, and the details of the technical scheme of the computing device that are not described in detail can be referred to the description of the technical scheme of the data processing method.

[0153] An embodiment of the present application further provides a computer readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the data processing method.

[0154] The above is a schematic scheme of the computer readable storage medium of the embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the data processing method described above belong to the same concept, and the details of the technical scheme of the storage medium that are not described in detail can be referred to the description of the technical scheme of the data processing method.

[0155] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order and still accomplish desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order to achieve desirable results. In certain implementations, multitasking and parallel processing can be advantageous.

[0156] The computer instructions include computer program code, which can be in the form of source code, object code, executable code, or some intermediate form. The computer readable medium can include any entity or apparatus capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer readable medium can be appropriately increased or decreased according to the requirements of patent practice, for example, according to the patent practice in some regions, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0157] It should be noted that for each method embodiment described above, in order to facilitate description, each method embodiment is described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0158] In the above-described embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0159] The preferred embodiments of the application disclosed above are only used to illustrate the application. The alternative embodiments do not describe all the details and limit the application to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of the application. The application selects and describes these embodiments in order to better explain the principles and practical applications of the application, so that those skilled in the art can well understand and utilize the application. The application is limited by the claims and their full scope and equivalents.

Claims

1. A data processing method, characterized in that, include: Receive natural language questions targeting specific business functions; The natural language question is processed by a third-party language parsing tool to obtain business credential data. This business credential data is determined within a preset business service via a credential query link. The process includes: establishing a credential query link between the preset business service and the third-party language parsing tool; receiving a business query request generated by the third-party language parsing tool based on the natural language question; and sending the business credential data to the third-party language parsing tool via the credential query link in response to the business query request. Based on the business credential data, the target business data corresponding to the business credential data is determined by querying the preset business service through the data query link.

2. The method as described in claim 1, characterized in that, In response to the business query request, business credential data is sent to the third-party language parsing tool via the credential query link, including: In response to the business query request, at least one business interface call request is generated; The target business data corresponding to the business query request is determined based on the call requests of each business interface. Generate business credential data corresponding to the target business data, and send the business credential data to the third-party language parsing tool through the credential query link.

3. The method as described in claim 2, characterized in that, The method further includes: If the business credential data meets the credential deletion conditions, the business credential data shall be deleted.

4. The method as described in claim 3, characterized in that, The conditions for deleting credentials include: The number of times the business credential data is used is greater than or equal to a preset threshold; and / or, The credential generation duration of the business credential data is greater than or equal to a preset duration threshold.

5. The method as described in claim 2, characterized in that, The target business data corresponding to the business query request is determined based on the call requests of each business interface, including: Determine the order in which requests are made to each business interface; Based on the calling order, the business interfaces corresponding to each business interface call request are called sequentially to communicate with the preset business service and obtain the target business data.

6. The method as described in claim 1, characterized in that, Receive natural language questions targeting specific business functions, including: The user interface is displayed to the user based on the user's request. Receive natural language questions from users based on the user interface, targeting specific services.

7. The method as described in claim 6, characterized in that, The method further includes: Receive the user's username and password; Verify the user's identity information based on the username and password; Accordingly, based on the business credential data, the target business data corresponding to the business credential data is determined by querying the preset business service through a data query link, including: If the user identity information is verified, the target business data corresponding to the business credential data is determined by querying the preset business service through the data query link based on the business credential data.

8. A data processing apparatus, characterized in that, include: The receiving module is configured to receive natural language questions targeting the desired service. The acquisition module is configured to process the natural language question using a third-party language parsing tool to obtain business credential data. The business credential data is determined in a preset business service via a credential query link. The process of obtaining the business credential data by processing the natural language question using the third-party language parsing tool includes: establishing a credential query link between the preset business service and the third-party language parsing tool; receiving a business query request generated by the third-party language parsing tool based on the natural language question using the credential query link; and sending the business credential data to the third-party language parsing tool via the credential query link in response to the business query request. The determination module is configured to query the preset business service based on the business credential data through a data query link to determine the target business data corresponding to the business credential data.

9. A computing device, comprising a memory, a processor, and computer instructions stored in the memory and executable on the processor, characterized in that, When the processor executes the computer instructions, it implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions, characterized in that, When executed by a processor, the computer instructions implement the steps of the method according to any one of claims 1-7.

Images