Data generation method and apparatus, and device and medium

Abstract

To provide a data generation method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product for realizing interaction with a user by generating an answer based on the content of a user query.SOLUTION: A data generation method comprises: generating first answer data based on first query data from a user; determining a first reconsideration result on the first answer data based on the first answer data and negative feedback in response to receiving the negative feedback of the user on the first answer data, wherein the first reconsideration result indicates a diagnostic reason why the user feedback on the first answer data is negative feedback; and generating second answer data on the first query data based on the first query data and the first reconsideration result.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to fields such as natural language processing and deep learning, and more particularly to a data generation method, an apparatus, an electronic device, a computer-readable storage medium and a computer program product. [Background technology]

[0002] Artificial intelligence is a field that studies how computers can imitate some human thought processes and intelligent behaviors (e.g., learning, reasoning, thinking, planning, etc.), and includes both hardware and software technologies. Artificial intelligence hardware technologies generally include sensors, artificial intelligence dedicated chips, cloud computing, distributed storage, big data processing, and other technologies, while artificial intelligence software technologies mainly include computer vision technology, voice recognition technology, natural language processing technology, machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0003] The generative language megamodel can be applied to various natural language processing tasks, in particular to realize interaction with users by generating natural language text as an answer based on the content of a user's query.

[0004] The methods described in this section are not necessarily methods that have been previously conceived or adopted. Unless otherwise noted, any methods described in this section should not be considered prior art merely by their inclusion in this section. Similarly, unless otherwise noted, the subject matter addressed in this section should not be considered an admission of any prior art. Summary of the Invention

[0005] The present disclosure provides a data generation method, apparatus, electronic device, computer-readable storage medium, and computer program product.

[0006] According to one aspect of the present disclosure, a data generation method is provided, the method including: generating first answer data based on first query data from a user; in response to receiving negative feedback from the user on the first answer data, determining a first reconsideration result for the first answer data based on the first answer data and the negative feedback, the first reconsideration result indicating a diagnostic reason why the user's feedback on the first answer data is negative feedback; and generating second answer data for the first query data based on the first query data and the first reconsideration result.

[0007] According to another aspect of the present disclosure, there is provided a data generating apparatus, the apparatus including: a first generating unit configured to generate first answer data based on first query data from a user; a determining unit configured in response to receiving negative feedback of the user on the first answer data to determine a first reconsideration result for the first answer data based on the first answer data and the negative feedback, the first reconsideration result indicating a diagnostic reason why the user's feedback on the first answer data is negative feedback; and a second generating unit configured to generate second answer data for the first query data based on the first query data and the first reconsideration result.

[0008] According to another aspect of the present disclosure, there is provided an electronic device including at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the data generation method described above.

[0009] According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having computer instructions stored thereon, the computer instructions being adapted to cause the computer to perform the data generation method described above.

[0010] According to another aspect of the present disclosure, there is provided a computer program product including a computer program, which when executed by a processor is capable of implementing the data generation method as described above.

[0011] According to one or more embodiments of the present disclosure, the quality of response data generation can be improved.

[0012] It should be understood that the subject matter described in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the disclosure will be readily apparent from the following specification. [Brief description of the drawings]

[0013] The drawings illustratively illustrate the examples, constitute a part of the specification, and together with the written description serve to explain exemplary embodiments of the examples. The illustrated examples are for illustrative purposes only and are not intended to limit the scope of the claims. In all the drawings, the same reference numerals refer to similar, but not necessarily identical, elements. [Figure 1] FIG. 1 is a schematic diagram illustrating an example system capable of implementing various methods described herein, according to an example embodiment of the present disclosure. [Diagram 2] 4 is a flowchart illustrating a data generation method according to an exemplary embodiment of the present disclosure. [Diagram 3] FIG. 2 is a schematic diagram illustrating a data generation process according to an exemplary embodiment of the present disclosure. [Figure 4] FIG. 2 is a block diagram illustrating a data generating device according to an exemplary embodiment of the present disclosure. [Diagram 5]FIG. 1 is a block diagram illustrating an example electronic device that can be used to implement an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, exemplary embodiments of the present disclosure will be described in conjunction with the drawings, and various details in the embodiments of the present disclosure contained therein are to be considered as merely illustrative, in order to facilitate understanding. Therefore, it should be recognized that those skilled in the art can make various changes and modifications to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the following description omits descriptions of known functions and structures.

[0015] In this disclosure, unless otherwise specified, the use of terms such as "first", "second", etc. to describe various elements is not intended to limit the location, timing, or importance of these elements. Such terms are used only to distinguish one element from another. In some instances, a first element and a second element may refer to the same instance of the element, or in some cases, may refer to different instances based on the contextual description.

[0016] The terms used in the description of the various examples of the present disclosure are intended only to describe specific examples and are not intended to be limiting. Unless otherwise clearly indicated by the context, the elements may be one or more unless the number of elements is specifically limited. In addition, the term "and / or" used in the present disclosure covers any and all possible combinations of the listed items.

[0017] In the related art, when a generative language model is applied to generate answer data based on user input data, the performance of the model is improved by manually labeling the corpus in the model training stage or adjusting the training method (e.g., optimizing the loss function or performing reinforcement learning). In addition, in the model application stage, i.e., the data generation process, answer data is usually directly generated only based on the query data input by the user, but it is not possible to adjust the corresponding answer data according to the user's feedback on the answer data, so the quality of the answer data cannot fully meet the needs of the user.

[0018] Based on this, the present disclosure provides a data generation method, which generates initial answer data for a user's query data, and then, when the user gives negative feedback on the answer data, self-diagnoses the reason why the answer data has received the negative feedback based on the negative feedback, and further generates a reconsideration result for the answer data, thereby generating new answer data based on the reconsideration result, thereby making the answer data more in line with the user's needs and improving the quality of the generation of the answer data.

[0019] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings.

[0020] 1 illustrates a schematic diagram of an example system 100 in which various methods and apparatus described herein may be implemented, according to embodiments of the present disclosure. With reference to FIG. 1, the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

[0021] In an embodiment of the present disclosure, the server 120 may execute one or more services or software applications that enable the execution of data generation methods.

[0022] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtualized and virtualized environments. In some embodiments, these services may be provided as web-based or cloud services, for example, provided to users of client devices 101, 102, 103, 104, 105, and / or 106 in a Software-as-a-Service (SaaS) model.

[0023] In the arrangement shown in FIG. 1, server 120 may include one or more assemblies that implement the functions performed by server 120. These assemblies may include software assemblies, hardware assemblies, or a combination thereof that may be executed on one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn use one or more client applications to interact with server 120 to utilize the services provided by these assemblies. It should be understood that a variety of different system arrangements are possible and may differ from system 100. Thus, FIG. 1 is an example of a system for implementing various methods described herein and is not intended to be limiting.

[0024] A user may use client devices 101, 102, 103, 104, 105, and / or 106 to submit query data and feedback. The client devices may provide an interface through which a user of the client device interacts with the client device. The client devices may also output information to the user through the interface. Although only six client devices are shown in FIG. 1, one skilled in the art will appreciate that the present disclosure may support any number of client devices.

[0025] The client devices 101, 102, 103, 104, 105, and / or 106 may include various types of computing devices, such as portable handheld devices, general purpose computers (e.g., personal computers or laptops), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors, or other sensing devices. These computing devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (e.g., GOOGLE Chrome OS), and may include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android, and the like. Portable handheld devices may include mobile phones, intelligent phones, tablets, personal digital assistants (PDAs), and the like. Wearable devices may include head-mounted displays (e.g., smart glasses) and other devices. Gaming systems may include various handheld gaming devices, Internet-enabled gaming devices, and the like. The client devices may run a variety of applications, such as Internet-related applications, communication applications (eg, email applications), Short Message Service (SMS) applications, and may use a variety of communication protocols.

[0026] Network 110 may be any type of network known to those skilled in the art that may use any one of a number of available protocols (including, but not limited to, TCP / IP, SNA, IPX, etc.) to support data communications. By way of example, one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token loop, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0027] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframes, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture involving virtualization (e.g., one or more flexible pools of virtualized logical storage devices to maintain the server's virtual storage devices). In various embodiments, server 120 may execute one or more services or software applications that provide the functionality described below.

[0028] The computing units in server 120 may run one or more operating systems, including any of the operating systems listed above and any commercially available server operating system. Server 120 may also run any one of a variety of additional server applications and / or mid-tier applications, including an HTTP server, an FTP server, a CGI server, a JAVA server, a database server, etc.

[0029] In some embodiments, server 120 may include one or more applications for analyzing and consolidating data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may include one or more applications for displaying data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0030] In some embodiments, the server 120 may be a server of a distributed system or a server incorporating blockchain. The server 120 may be a cloud server, or an intelligent cloud computing server or an intelligent cloud host equipped with artificial intelligence technology. The cloud server is a host product in a cloud computing service system, and solves the defects of the traditional physical host and virtual private server (VPS) services, such as high management difficulty and low business scalability.

[0031] System 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data or other information. For example, one or more of databases 130 may be used to store information such as audio files or video files. Databases 130 may be located in a variety of locations. For example, a database used by server 120 may be local to server 120 or may be remote from server 120 and in communication with server 120 over a network or a dedicated connection. Databases 130 may be of different types. In some embodiments, a database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve data from the database and from the database in response to instructions.

[0032] In some embodiments, one or more of databases 130 may be used by an application to store data for the application. The databases used by an application may be different types of databases, such as a key-value repository, an object repository, a general-purpose repository backed by a file system, etc.

[0033] The system 100 of FIG. 1 can be configured and operated in a variety of ways to accommodate the application of the various methods and apparatus described in accordance with this disclosure.

[0034] 2 illustrates a flow diagram of a data generation method 200 according to an exemplary embodiment of the present disclosure. As shown in FIG. 2, the method 200 includes: A step S201 of generating first answer data based on first query data from a user; S202 in response to receiving the user's negative feedback on the first answer data, determining a first reconsideration result on the first answer data based on the first answer data and the negative feedback, the first reconsideration result indicating a diagnostic reason that the user's feedback on the first answer data is negative feedback; and generating second response data to the first query data based on the first query data and the first reconsideration result.

[0035] According to the data generation method described in method 200, after generating first answer data for query data input by a user, if negative feedback from the user for the first answer data is received, a reconsideration result for the first answer data is generated based on the negative feedback, thereby achieving self-diagnosis; and further, based on the reconsideration result, new second answer data is generated so that the new second answer data is more in line with the user's needs, thereby improving the quality of answer data generation.

[0036] In some examples, the first query data, the first answer data, the second answer data and the first reconsideration result may be natural language text. For example, the first query data may be "Please write a catchphrase for a car with 5 words", in such a case, if the generated first answer data is a catchphrase containing 7 words, and the user gives negative feedback to the first answer data, the first reconsideration result of "the user's request is a catchphrase with 5 words, the generated result contains 7 words, and the number of words does not meet the user's request" can be obtained by self-diagnosing the reason for receiving the negative feedback, and the first reconsideration result can be used to indicate the possible cause of the first answer data getting negative feedback, and based on that, new second answer data can be generated, thereby avoiding the second answer data receiving negative feedback from the user again, thereby improving the quality of the generation of answer data.

[0037] According to some embodiments, the first reconsideration result further includes an optimization policy for the first answer data, so that data can be generated based on the reconsideration result further including the optimization policy, thereby obtaining second answer data that is more targeted, richer in content, and more specific based on the reconsideration result.

[0038] In the above example, the reconsideration result may be "the user's request is a catchphrase of 5 words, the generated result contains 7 words, the number of words does not match the user's request, and it is necessary to ensure that the result contains 5 words when regenerating." By generating new second answer data based on the reconsideration result including the optimization policy of "it is necessary to ensure that the result contains 5 words when regenerating," it is possible to improve the quality of the generation of the second answer data and further improve the user experience.

[0039] According to some embodiments, in step S201, generating first answer data based on first query data from a user includes: determining, based on the first query data, first input data to be used in a deep learning model for generating answer data based on input data; and inputting the first input data into the deep learning model to obtain the first answer data; and in step S203, generating second answer data to the first query data based on the first query data and the first reconsidered result includes: determining, based on the first query data and the first reconsidered result, second input data to be used in the deep learning model; and inputting the second input data into the deep learning model to obtain the second answer data. This allows answer data to be generated using a deep learning model, and first input data and second input data indicating different needs are generated and input into the deep learning model, i.e., the same deep learning model is used to generate the first answer data and the second answer data, thereby improving efficiency and convenience.

[0040] In some examples, the deep learning model for generating answer data based on input data has an end-to-end characteristic, and can directly generate answer data in a natural language text format based on input data in a natural language text format. In some examples, the deep learning model can adopt an N-layer Transformer network structure having an encoder and a decoder, or a Unified pre-trained Language Model (UniLM) network structure. It should be understood that the deep learning model may be a neural network model based on other Transformer network structures, and is not limited thereto.

[0041] In some examples, the deep learning model can be obtained by training using a sample corpus, and the sample corpus for training the deep learning model may include, for example, sample input data and sample answer data for the sample input data. In the training process, the sample input data can be input into the deep learning model to obtain predicted answer data, a loss value can be calculated based on the predicted answer data and the sample answer data, and the parameters of the deep learning model can be adjusted based on the loss value. In some examples, the loss value of the deep learning model can be determined based on a Negative-Log Likelihood Loss (NLL) calculation method.

[0042] In some examples, the deep learning model applied in step S201 and the deep learning model applied in step S203 may also be trained using different corpora, such that the use of a more directional training corpus can improve the accuracy of the answers generated by the models.

[0043] According to some embodiments, determining second input data for the deep learning model based on the first query data and the first rethinking result includes determining the second input data based on the first query data, the first rethinking result, and task description information indicating that the second input data includes the first rethinking result, whereby adding task description information based on the input content can explicitly indicate current data generation needs, and the deep learning model can generate second input data based on the first rethinking result and the first query data to improve data generation efficiency.

[0044] With reference to the above example, in one example, the first query data, the first answer data, the second answer data and the first reconsideration result are all natural language texts, and the deep learning model is also used to receive and generate the natural language texts. In this case, the task description information may be a pre-defined natural language text segment or template for indicating the presence of the first query data and the first reconsideration result in the input data, and the task description information may be, for example, "based on the first query data __ and the first reconsideration result __, generate answer data for the first query data." By filling the content of the first query data and the first reconsideration result into the template, input data that can clearly indicate the need for data generation can be obtained, and the deep learning model can generate the second answer data based on the template.

[0045] It should be understood that the above embodiment is merely an example of the input data of the deep learning model, and the input data can also be generated based on other manners, for example, based on the first query data and the first reconsideration result, a label of a predefined generation pattern is directly added to obtain the second input data, and the deep learning model determines that the second input data contains the first reconsideration result based on the tag. As long as the deep learning model can sense the existence of the reconsideration result in the input data and generate answer data based on the reconsideration result, the present disclosure does not limit the manner of determining the input data.

[0046] According to some embodiments, in step S202, determining a first reconsideration result for the first answer data based on the first answer data and the first feedback includes inputting the first answer data and the first feedback into a reconsideration generation network to obtain the first reconsideration result output by the reconsideration generation network, where the reconsideration generation network is obtained by training using a sample corpus, the sample corpus including sample answer data, sample feedback, and sample reconsideration results for the sample answer data, thereby obtaining the reconsideration result using the trained reconsideration generation network, and improving the efficiency and convenience of generating the reconsideration result.

[0047] In some examples, the rethinking generation network may adopt an N-layer Transformer network structure having an encoder and a decoder, or a Unified Pre-Trained Language Model (UniLM) network structure. Similar to the training method of the deep learning model described above, the rethinking generation network may be obtained by training using a sample corpus, and the sample corpus for training the rethinking generation network may include, for example, sample answer data, sample feedback, and sample rethinking results for the sample answer data. In the training process, the sample answer data and sample feedback are input into the deep learning model to obtain a predicted rethinking result, a loss value is calculated based on the predicted rethinking result and the sample rethinking result, and the parameters of the rethinking generation network may be adjusted based on the loss value.

[0048] According to some embodiments, in step S202, in response to receiving the user's negative feedback for the first answer data, determining a first reconsideration result for the first answer data based on the first answer data and the negative feedback includes determining a first reconsideration result for the first answer data based on the first answer data and the first feedback in response to receiving the user's first feedback for the first answer data and determining that the first feedback is negative feedback, so that after obtaining the user's feedback data, the feedback data can be further determined to be negative feedback, so that when the feedback data does not explicitly indicate whether the feedback is negative feedback, the determination step can further identify negative feedback and improve accuracy.

[0049] In some examples, a classifier-based user feedback recognition model can be utilized to distinguish whether the first feedback is negative feedback. In some examples, the user feedback recognition model can be trained using a sample feedback dataset with real attribute labels (including positive feedback and negative feedback), thereby more efficiently and accurately determining whether the first feedback from the user is negative feedback.

[0050] In some examples, whether negative feedback from a user has been received may also be determined in other manners. In one example, negative feedback may be determined to be received based on a user's interaction with a user interface, such as in response to determining that the user clicked a bad rating button or provided a score below a threshold.

[0051] According to some embodiments, the method 200 further includes, in response to determining that the similarity between the second query data from the user and the first query data is greater than a preset threshold, generating third answer data to the second query data based on the first query data, the second answer data, and the second query data, so that when a user submits second query data similar to the first query data, the first query data and the second answer data can be utilized to enhance the generation of the current third answer data, and improve the quality of the generation of the answer data.

[0052] In some examples, the similarity between the first query data and the second query data can be determined by representing both query data as text vectors and calculating the vector similarity.

[0053] According to some embodiments, the method 200 further includes storing the first query data and the second answer data in a memory bank, where the step of generating third answer data for the second query data based on the first query data, the second answer data, and the second query data in response to determining that the similarity between the second query data from the user and the first query data in the memory bank is greater than the preset threshold includes: retrieving the second answer data from the memory bank in response to determining that the similarity between the second query data from the user and the first query data in the memory bank is greater than the preset threshold; and generating the third answer data based on the first query data, the second answer data, and the second query data. This allows the memory bank to be used to store query data-answer data pairs, and the memory bank can be used to store a larger number and a longer period of historical interaction data, and further to enhance the generation of current answer data by referring to historical interactions, thereby improving the quality of the generation of answer data.

[0054] In some examples, when using the above-mentioned deep learning model to generate answer data, third input data for the deep learning model can be determined based on the first query data, the second answer data, and the second query data, and the third input data can be input to the deep learning model to obtain the third answer data. In one example, the third answer data may include, for example, explanatory information indicating the existence of the first query data and the second answer data, such that the deep learning model can generate the third answer data based thereon.

[0055] 3 shows a schematic diagram of a data generation process according to an exemplary embodiment of the present disclosure. As shown in FIG. 3, in one example, the data generation process may be implemented to interact with a user using an intelligent dialogue system 300.

[0056] Referring to FIG. 3 , the intelligent dialogue system 300 includes a user feedback recognition model 301, a reflexive generative network 302, a deep learning model 303, and a memory bank 304.

[0057] In one example, the data transmission path including the user feedback recognition model 301, the rethinking generation network 302, and the memory bank 304 is optional. When the user sends the first query data and the memory bank 304 does not contain the history data similar to the first query data, the deep learning model 303 can directly generate the first answer data according to the first query data input by the user. After receiving the user's first feedback for the first answer data, the user feedback recognition model 301 can be used to determine whether the first feedback is negative feedback, and if it is determined that the first feedback is negative feedback, the rethinking generation network 302 can be used to obtain a first rethinking result according to the first answer data and the first feedback, and the deep learning model 303 can be used to determine new second answer data according to the first query data and the first rethinking result, and the first query data and the second answer data can be stored in the memory bank 304.

[0058] When receiving second query data and determining that first query data similar to the second query data 304 already exists in the memory bank 304, the deep learning model 303 determines third answer data for the second query data based on the first query data, the second answer data, and the second query data, so that the first query data and the second answer data can be utilized to enhance the current generation of the third answer data and improve the quality of the generation of the answer data.

[0059] According to an embodiment of the present disclosure, a data generating device is further provided. FIG. 4 shows a configuration block diagram of a data generating device 400 according to an exemplary embodiment of the present disclosure. As shown in FIG. 4, the device 400 includes: a first generating unit 401 configured to generate first answer data based on first query data from a user; a determining unit 402 configured to determine a first reconsideration result for the first answer data based on the first answer data and the negative feedback in response to receiving the user's negative feedback for the first answer data, the first reconsideration result indicating a diagnostic reason why the user's feedback for the first answer data is negative feedback; and a second generating unit 403 configured to generate second answer data for the first query data based on the first query data and the first reconsideration result.

[0060] According to some embodiments, the first generation unit 401 includes a first determination subunit configured to determine, based on the first query data, first input data to be used in a deep learning model for generating answer data based on input data, and a first input subunit configured to input the first input data to the deep learning model to obtain the first answer data, wherein the second generation unit 403 includes a second determination subunit configured to determine, based on the first query data and the first reconsideration result, second input data to be used in the deep learning model, and a second input subunit configured to input the second input data to the deep learning model to obtain the second answer data.

[0061] According to some embodiments, the second input subunit is configured to determine the second input data based on the first query data, the first reconsideration result, and task description information indicating that the second input data includes the first reconsideration result.

[0062] According to some embodiments, the determination unit 402 inputs the first answer data and the first feedback into a reconsideration generation network to obtain the first reconsideration result output by the reconsideration generation network, where the reconsideration generation network is obtained by training using a sample corpus, and the sample corpus is configured to include sample answer data, sample feedback, and sample reconsideration results for the sample answer data.

[0063] According to some embodiments, the determination unit 402 is configured to determine a first reconsideration result for the first answer data based on the first answer data and the first feedback in response to receiving a first feedback of the user on the first answer data and in response to determining that the first feedback is negative feedback.

[0064] According to some embodiments, the apparatus 400 further includes a third generation unit configured to generate third answer data to the second query data based on the first query data, the second answer data, and the second query data in response to determining that a similarity between second query data from a user and the first query data is greater than a preset threshold.

[0065] According to some embodiments, the apparatus 400 further includes a storage unit configured to store the first query data and the second answer data in a memory bank, where the third generation unit includes an acquisition subunit configured to acquire the second answer data from the memory bank in response to determining that a similarity between the second query data from a user and the first query data in the memory bank is greater than the preset threshold, and a generation subunit configured to generate the third answer data based on the first query data, the second answer data, and the second query data.

[0066] According to some embodiments, the first reconsideration result further includes an optimization policy for the first answer data.

[0067] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of relevant user personal information shall all comply with the provisions of relevant laws and regulations and not violate public order and morals.

[0068] According to another aspect of the present disclosure, there is further provided an electronic device including at least one processor and a memory communicatively connected to the at least one processor, the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the data generation method described above.

[0069] According to another aspect of the present disclosure, there is further provided a non-transitory computer readable storage medium having computer instructions stored thereon, the computer instructions being used to cause the computer to perform the data generation method described above.

[0070] According to another aspect of the present disclosure there is further provided a computer program product including a computer program which, when executed by a processor, implements the data generation method as described above.

[0071] Referring to FIG. 5, a block diagram of an electronic device 500 functioning as a server or client of the present disclosure will be described, which is an example of a hardware device applicable to each aspect of the present disclosure. The electronic device may represent various forms of digital electronic computing devices, such as laptop computers, desktop computers, stages, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, mobile phones, intelligent phones, wearable devices, and other similar computing devices. The components, their connections, and their functions shown herein are merely exemplary and do not limit the implementation of the present disclosure as described and / or claimed herein.

[0072] 5, the device 500 includes a computing unit 501, which can perform various suitable operations and processes according to a computer program stored in a read-only memory (ROM) 502 or loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for operating the device 500 may be stored. The computing unit 501, the ROM 502 and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0073] The components in the device 500 are connected to an I / O interface 505, which includes an input unit 506, an output unit 507, a storage unit 508, and a communication unit 509. The input unit 506 may be any type of device capable of inputting information to the device 500, and the input unit 506 can receive input numeric or character information and generate key signal inputs for user settings and / or function control of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a track board, a track ball, a control lever, a microphone, and / or a remote control. The output unit 507 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 508 may include, but is not limited to, a magnetic disk, an optical disk. The communication unit 509 enables the device 500 to exchange information / data with other devices via a computer network, e.g., the Internet, and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, e.g., a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0074] The computing unit 501 may be various general-purpose and / or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that execute machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 executes each of the methods and processes described in the preceding sentence, such as the data generation method. For example, in some embodiments, the data generation method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, some or all of the computer program may be loaded and / or installed in the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the data generation method described above may be performed. Alternatively, in another embodiment, the computing unit 501 may be configured to execute the data generation method in any other suitable manner (e.g., by firmware).

[0075] Various embodiments of the systems and techniques described herein may be implemented in digital electronic circuitry systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may be embodied in one or more computer programs that may be executed and / or interpreted by a programmable system that includes at least one programmable processor, which may be a special purpose or general purpose programmable processor, and may receive data and instructions from a storage system, at least one input device, and at least one output device, and may transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0076] The program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, a special purpose computer or other programmable data processing apparatus, and when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are performed. The program codes may be entirely executed on a machine, partly executed on a machine, partly executed on a machine and partly executed on a remote machine as an independent software package, or entirely executed on a remote machine or server.

[0077] In the context of this disclosure, a machine-readable medium may be a tangible medium, which may include or store a program for use in or in conjunction with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples of machine-readable storage media include an electrical connection by one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0078] To provide for interaction with a user, a computer may implement the systems and techniques described herein and include a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user, and a keyboard and pointing device (e.g., a mouse or trackball) through which a user may provide input to the computer. Other types of devices may also be provided for providing interaction with a user, for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or haptic feedback) and may receive input from the user in any form (including sound input, speech input, or tactile input).

[0079] The systems and techniques described herein may be implemented in a computing system including a backstage component (e.g., as a data server), a middleware component (e.g., an application server), a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with embodiments of the systems and techniques described herein), or any combination of such background, middleware, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0080] The computer system may include a client side and a server. The client side and the server are generally remote from each other and usually interact with each other via a communication network. The relationship between the client side and the server is generated by running computer programs having a client side-server relationship with each other on corresponding computers. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0081] It should be understood that the steps may be reordered, added, or removed using the various forms of flow described above. For example, the steps described in this disclosure may be performed in parallel, sequentially, or in a different order, and the present disclosure is not limited thereto as long as the technical solutions disclosed in this disclosure can achieve the desired results.

[0082] Although the embodiments or examples of the present disclosure have been described with reference to the drawings, it should be understood that the above-mentioned methods, systems, and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples. Various elements of the embodiments or examples may be omitted or replaced by their equivalent elements. It should be noted that each step may be performed in a different order from the order described in this disclosure. Furthermore, various elements of the embodiments or examples may be combined in various ways. It is important to note that with the evolution of technology, many elements described herein may be replaced by equivalent elements that appear later in this disclosure.

Claims

1. 1. A method for generating data, the method comprising: generating first answer data based on first query data from a user; in response to receiving the user's negative feedback on the first answer data, determining a first reconsideration result on the first answer data based on the first answer data and the negative feedback, the first reconsideration result indicating a diagnostic reason why the user's feedback on the first answer data is negative feedback; generating second response data to the first query data based on the first query data and the first reconsideration result.

2. The generating of first answer data based on first query data from a user includes: determining, based on the first query data, first input data for use in a deep learning model to generate answer data based on input data; and inputting the first input data into the deep learning model to obtain the first response data; Here, generating second response data to the first query data based on the first query data and the first reconsideration result includes: determining second input data for use with the deep learning model based on the first query data and the first reconsideration result; and inputting the second input data into the deep learning model to obtain the second answer data.

3. determining second input data for use with the deep learning model based on the first query data and the first reconsideration result includes:

3. The method of claim 2, comprising determining the second input data based on the first query data, the first reconsideration result, and task description information indicating that the second input data includes the first reconsideration result.

4. Determining a first reconsideration result for the first response data based on the first response data and the first feedback includes: The method of any one of claims 1 to 3, further comprising: inputting the first answer data and the first feedback into a reconsideration generative network to obtain the first reconsideration result output by the reconsideration generative network, wherein the reconsideration generative network is obtained by training using a sample corpus, the sample corpus including sample answer data, sample feedback, and sample reconsideration results for the sample answer data.

5. In response to receiving the user's negative feedback on the first response data, determining a first reconsideration result on the first response data based on the first response data and the negative feedback includes: The method according to any one of claims 1 to 3, comprising: in response to receiving a first feedback of the user on the first answer data, and in response to determining that the first feedback is negative feedback, determining a first reconsideration result on the first answer data based on the first answer data and the first feedback.

6. The method according to any one of claims 1 to 3, further comprising: generating third answer data to the second query data based on the first query data, the second answer data, and the second query data in response to determining that a similarity between second query data from a user and the first query data is greater than a preset threshold.

7. storing the first query data and the second response data in a memory bank; generating third response data to the second query data based on the first query data, the second response data, and the second query data in response to determining that a similarity between the second query data from a user and the first query data is greater than a preset threshold value, acquiring the second response data from the memory bank in response to determining that a similarity between second query data from a user and the first query data in the memory bank is greater than the preset threshold; 7. The method of claim 6, comprising: generating the third answer data based on the first query data, the second answer data, and the second query data.

8. The method according to any one of claims 1 to 3, wherein the first reconsideration result further comprises an optimization policy for the first answer data.

9. 1. A data generating device, comprising: A first generating unit configured to generate first answer data based on first query data from a user; a determining unit configured to determine a first reconsideration result for the first answer data based on the first answer data and the negative feedback in response to receiving the user's negative feedback for the first answer data, the first reconsideration result indicating a diagnostic reason that the user's feedback for the first answer data is negative feedback; a second generating unit configured to generate second answer data to the first query data based on the first query data and the first reconsideration result.

10. The first generating unit comprises: a first determination subunit configured to determine, based on the first query data, first input data used in a deep learning model for generating answer data based on input data; a first input subunit configured to input the first input data to the deep learning model to obtain the first answer data; The second generating unit is a second determination subunit configured to determine second input data for use in the deep learning model based on the first query data and the first reconsideration result; and a second input subunit configured to input the second input data to the deep learning model to obtain the second answer data.

11. The second input subunit:

11. The apparatus of claim 10, configured to determine the second input data based on the first query data, the first reconsideration result, and task description information indicating the second input data includes the first reconsideration result.

12. The determination unit is The apparatus of any one of claims 9 to 11, further comprising: inputting the first answer data and the first feedback into a reconsideration generative network to obtain the first reconsideration result output by the reconsideration generative network, wherein the reconsideration generative network is obtained by training using a sample corpus, and the sample corpus is configured to include sample answer data, sample feedback, and sample reconsideration results for the sample answer data.

13. The determination unit is The device according to any one of claims 9 to 11, configured to, in response to receiving a first feedback of the user on the first answer data and in response to determining that the first feedback is negative feedback, determine a first reconsideration result on the first answer data based on the first answer data and the first feedback.

14. The apparatus according to any one of claims 9 to 11, further comprising a third generating unit configured to generate third answer data to the second query data based on the first query data, the second answer data, and the second query data in response to determining that a similarity between second query data from a user and the first query data is greater than a preset threshold.

15. a storage unit configured to store the first query data and the second answer data in a memory bank; The third generation unit is an acquiring subunit configured to acquire the second answer data from the memory bank in response to determining that a similarity between the second query data from the user and the first query data in the memory bank is greater than the preset threshold; The apparatus of claim 14 , further comprising: a generating subunit configured to generate the first query data, the second answer data, and the third answer data based on the second query data.

16. The apparatus according to any one of claims 9 to 11, wherein the first reconsideration result further comprises an optimization policy for the first answer data.

17. An electronic device, At least one processor; a memory communicatively coupled to the at least one processor; An electronic device, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the method of claim 1.

18. 13. A non-transitory computer readable storage medium having computer instructions stored thereon, the computer instructions being used to cause a computer to perform the method of claim 1.

19. A computer program product comprising a computer program which, when executed by a processor, implements the method of claim 1.

Images