Information processing method and device, equipment and storage medium

Abstract

Embodiments of the present disclosure provide information processing methods, apparatuses, devices and storage media. The method comprises: obtaining a first instruction generated by a target model, the first instruction being used for processing a target task associated with a user input; in response to detecting that a first error occurs in execution of the first instruction, determining a target error sample matching the first error from an error sample set, the error samples in the error sample set corresponding to instruction execution errors; and providing the target error sample to the target model to obtain a second instruction for processing the target task. Thus, the model learns the errors in the previous generation process through the error sample to avoid the recurrence of the errors. This can realize automatic correction of the instruction and help improve the efficiency and accuracy of processing the user input.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to information processing methods, apparatus, devices, and computer-readable storage media. Background Technology

[0002] With the development of information technology, various terminal devices can provide people with a variety of services in work and life. Applications providing these services can be deployed on these terminal devices. The terminal devices present relevant content and interact with users through the application's user interface, meeting various user needs. In some cases, applications can utilize models to perform tasks. However, models may encounter anomalies during task execution. Therefore, improving the stability and accuracy of model operation is a key concern. Summary of the Invention

[0003] In a first aspect of this disclosure, an information processing method is provided. The method includes: acquiring a first instruction generated by a target model, the first instruction being used to process a target task associated with user input; in response to detecting a first error in the execution of the first instruction, determining a target error sample matching the first error from an error sample set, the error sample in the error sample set corresponding to an instruction execution error; and providing the target error sample to the target model to obtain a second instruction for processing the target task.

[0004] In a second aspect of this disclosure, an apparatus for information processing is provided. The apparatus includes: a first instruction generation module configured to acquire a first instruction generated by a target model, the first instruction being used to process a target task associated with user input; an error sample determination module configured to, in response to detecting a first error in the execution of the first instruction, determine a target error sample from an error sample set matching the first error, the error sample in the error sample set corresponding to an instruction execution error; and a second instruction acquisition module configured to provide the target error sample to the target model to obtain a second instruction for processing the target task.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the electronic device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. A computer program is stored on the medium, which, when executed by a processor, implements the method of the first aspect.

[0007] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, it implements the method according to a first aspect of this disclosure.

[0008] It should be understood that the description in this section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram of an example environment in which embodiments of the present disclosure can be implemented is shown;

[0011] Figure 2 A flowchart illustrating an information processing procedure according to some embodiments of the present disclosure is shown;

[0012] Figure 3 Schematic diagrams illustrating examples of some embodiments according to this disclosure are shown;

[0013] Figure 4 A schematic structural block diagram of an apparatus for information processing according to some embodiments of the present disclosure is shown;

[0014] Figure 5 A block diagram of an electronic device that can implement one or more embodiments of the present disclosure is shown. Detailed Implementation

[0015] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0016] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0017] In this document, unless explicitly stated otherwise, performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.

[0018] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0019] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and authorization should be obtained from the relevant users. Among them, relevant users may include any type of rights holder, such as individuals, enterprises, and groups.

[0020] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly inform the user that the requested operation will require obtaining and using the user's information, thereby enabling the relevant user to choose whether to provide information to the software or hardware such as the electronic device, application, server, or storage medium that performs the operation of the technical solution disclosed herein based on the prompt message.

[0021] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide information to the electronic device.

[0022] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure. The activation of digital assistant-related functions, the acquisition of data, the processing and storage of data, etc., in the embodiments of this disclosure shall all require prior authorization from the user and other rights holders associated with the user, and shall comply with the agreements and rules between relevant laws and regulations and rights holders.

[0023] As used in this paper, the term "model" refers to a model that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs using multiple layers of processing units. A neural network model is an example of a deep learning-based model. In this paper, "model" may also be referred to as a "machine learning model," "learning model," "machine learning network," or "learning network," and these terms are used interchangeably.

[0024] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. Environment 100 relates to an application management platform 110, which can support the creation and / or execution of applications. In some embodiments, the portion of the application management platform 110 used to support application creation may also be referred to as an application creation portion. In some embodiments, the portion of the application management platform 110 used to support application execution may also be referred to as an application execution portion.

[0025] As shown in the figure, the application creation section provides an environment for user 105 to create and publish applications. User 105 can be referred to as the application creation user or creator. In some embodiments, the application creation section can be a low-code platform that provides a collection of tools for application creation. The application creation section can support visual development of various types of applications, allowing developers to skip the manual coding process and accelerate the application development cycle and reduce costs. The application creation section can support any suitable platform for users to develop one or more types of applications, such as an application platform as a service (aPaaS) based platform. Such a platform enables users to efficiently develop applications, enabling operations such as application creation and application function adjustment.

[0026] The application creation component can be deployed locally on user 105's terminal device and / or supported by a server-side device. For example, user 105's terminal device can run a client with the application creation component, which can support interaction between the user and the application creation component provided by the server. When the application creation component runs locally on the user's terminal device, user 105 can directly interact with the local application creation component using the terminal device. When the application creation component runs on a server-side device, the server-side device can provide services to the client running on the terminal device based on the communication connection with the terminal device. The application creation component can present a corresponding page 130 to user 105 based on user 105's actions, to output and / or receive application creation-related information from user 105.

[0027] In some embodiments, the application creation section may be associated with a corresponding database, which stores the data or information required for the application creation process supported by the application creation section. For example, the database may store the code and description information corresponding to the various functional modules that make up the application. The application creation section can also perform operations such as calling, adding, deleting, and updating the functional modules in the database. The database may also store operations that can be performed on different functional blocks. For example, in a scenario where an application needs to be created, the application creation section can call the corresponding functional blocks from the database to build the application.

[0028] In embodiments of this disclosure, user 105 can create and publish target application 120 as needed in the application creation section. Target application 120 can be published to any suitable application runtime section, as long as the application runtime section can support the operation of target application 120. After publication, target application 120 can be operated by one or more end users 145. End user 145 can operate target application 120 through an associated terminal device 146 and thereby interact with application management platform 110. End user 145 can be referred to as the end user of target application 120. In some embodiments, target application 120 may include or be implemented as digital assistant 122.

[0029] Digital assistant 122 can be configured to have intelligent conversational capabilities. In the example shown, digital assistant 122 can be integrated into target application 120, serving as part of target application 120 to assist in task processing within target application 120. In other examples, digital assistant 122 can be configured as a standalone application, such as a web application or other type of application. In such examples, digital assistant 122 and target application 120 can be considered as the same application. Digital assistant 122 is provided to assist users with various task processing needs in different applications and scenarios. During interaction with digital assistant 122, the user inputs interactive messages, and digital assistant 122 responds to the user's input by providing reply messages. Typically, digital assistant 122 can support users inputting questions in natural language and performs tasks and provides replies based on its understanding of natural language input and logical reasoning capabilities.

[0030] In some embodiments, the digital assistant 122 can interact with the end user 145 as a contact. For example, the digital assistant 122 can be implemented in an instant messaging (IM) application. The digital assistant 122 can interact with the end user 145 in a one-on-one chat session. In some embodiments, the digital assistant 122 can interact with multiple users in a group chat session that includes multiple users.

[0031] For each end user 145, the client of the application runtime portion can present an interaction window 142 of the target application 120 or digital assistant 122 in the client interface, such as a conversation window with the digital assistant 122. The end user 145 can enter conversation messages in the conversation window, and the target application 120 can determine the response message from the digital assistant 122 based on the created configuration information and present it to the user in the interaction window 142. In some embodiments, depending on the configuration of the target application 120, the interaction messages with the target application 120 can include multimodal messages, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and so on.

[0032] Similar to the application creation component, the application runtime component can be deployed locally on each end user's (145's) terminal device and / or supported by a server device. For example, the end user's (145's) terminal device can run a client with the application runtime component, which can support interaction between the user and the application runtime component provided by the server. When the application runtime component runs locally on the user's terminal device, the end user (145) can directly interact with the local application runtime component using the terminal device. When the application runtime component runs on a server device, the server device can provide services to the client running on the terminal device based on the communication connection with the terminal device. The application runtime component can present corresponding application pages to the end user (145) based on the user's (145's) actions, outputting and / or receiving application-related information from the user (145).

[0033] In some embodiments, the implementation of at least some functions of the target application 120, and / or the implementation of at least some functions of the digital assistant 122 within the target application 120, may be based on models. During the creation or operation of the target application 120, one or more models 155 may be invoked, such as the capabilities of model 155. In the target application 120, the digital assistant 122 may utilize model 155 to understand user input and provide responses to the user based on the output of model 155.

[0034] During the creation process, the application management platform 110 needs to use model 155 to test the target application 120 to determine whether the running results of the target application 120 meet expectations. During operation, in response to different operation requests from users of the target application 120, the application operation part may need to use model 155 to determine the response results to users.

[0035] Although shown as independent of the application management platform 110, one or more models 155 may run on the application management platform 110 or other remote servers. In some embodiments, model 155 may be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model may be based on a language model (LM). A language model, by learning from a large corpus, is capable of question answering. Model 155 may also be based on other suitable models.

[0036] The application management platform 110 can run on suitable electronic devices. These electronic devices can be any type of computing-capable device, including terminal devices or server devices. Terminal devices can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. Server devices can include, for example, computing systems / servers, such as mainframes, edge computing nodes, computing devices in cloud environments, and so on. In some embodiments, the management platform 110 can be implemented based on cloud services.

[0037] It should be understood that the structure and function of environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure. For example, although a single user interacting with the application creation section and a single user interacting with the application running section are illustrated, in reality multiple users can access application management platform 110 to each create a digital assistant, and each digital assistant can be used to interact with multiple users.

[0038] As mentioned earlier, applications can utilize models to perform tasks. During task execution, models may encounter exceptions. A common exception is that the instructions generated by the model fail to execute correctly, meaning the model generates incorrect instructions. In this case, it's usually necessary to interact with the model again. For example, the model can be instructed to regenerate the instructions. However, models are often unaware of the errors in their previously generated instructions, and without providing additional information, the regenerated instructions may still be incorrect. This can impact the efficiency of processing user input.

[0039] This disclosure provides an improved information processing scheme. In this scheme, a first instruction generated by a target model is obtained, the first instruction being used to process a target task associated with user input. In response to detecting a first error in the execution of the first instruction, a target error sample matching the first error is determined from an error sample set, the error sample in the error sample set corresponding to an instruction execution error. The target error sample is provided to the target model to obtain a second instruction for processing the target task.

[0040] In this way, when an error is detected during instruction execution, a target error sample matching the detected error can be identified from the error sample set. This error sample is then provided to the model to regenerate the instruction. In other words, the model learns from previous errors in the generation process using error samples to avoid recurrence. This enables automatic instruction correction, helping to improve the efficiency and accuracy of processing user input.

[0041] Some exemplary embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0042] The task management process described in the embodiments of this disclosure can be implemented on an application management platform, a terminal device with the application management platform installed, and / or a server corresponding to the application management platform. In the examples below, for the sake of discussion, the description is from the perspective of the application management platform, for example... Figure 1 The application management platform 110 is shown. The user interface presented by the application management platform 110 can be displayed via the terminal device of user 145, and the application management platform 110 can receive user input via the terminal device of user 145. In some embodiments of this disclosure, user 145 is the terminal user of the target application 120. It should be understood that the user interface presented by the application management platform 110 can also be displayed via the terminal device of user 105, and the application management platform 110 can also receive user input via the terminal device of user 105. In some embodiments of this disclosure, user 105 is the creator, manager, or maintainer of the target application 120.

[0043] Figure 2 A flowchart of an information processing procedure 200 according to some embodiments of the present disclosure is shown. Procedure 200 can be implemented in an application management platform 110, for example, by the application runtime portion of the application management platform 110. The following is in conjunction with... Figure 1 To describe Figure 2 The task processing procedure is shown.

[0044] In box 210, application management platform 110 obtains a first instruction generated by the target model, which is used to process the target task associated with user input.

[0045] In some embodiments, the application management platform 110 may receive user input (also referred to as target user input) from a target user (which may be any suitable user), for example, user input from user 145. Target user input can be of any suitable type, such as text, voice, gesture, etc. The application management platform 110 may receive user input via any suitable means, for example, via an input box for text, via a microphone for audio, etc. User input may be presented, for example, in an interactive window (e.g., interactive window 142).

[0046] The application management platform 110 can provide user input to the target model so that the target model can generate a first instruction based on the target user input. The target model can be deployed on the application management platform 110 or on a remote device. The target model can be based on any suitable model structure, including but not limited to Transformer models, convolutional neural networks (CNNs), recurrent neural networks (RNNs), deep neural networks (DNNs), and any suitable model. In some embodiments, the target model can be a language model.

[0047] The first instruction is used to process a target task associated with user input. In some embodiments, the target task may be a task directed at a data object, which may instruct an operation associated with the data object. The data object may include structured or unstructured information. For example, a data object may include a structured object, which is any suitable type of object capable of storing or representing information in a structured manner. Examples of structured objects may include, but are not limited to, data tables, databases, application programming interfaces (APIs), etc. Alternatively or additionally, a data object may include unstructured objects, such as emails, documents, knowledge bases, etc. The target task may include, for example, an analysis task of data in a data object (e.g., a data table), an update task of data in a data object, a knowledge question-and-answer task for a data object, etc.

[0048] The first instruction, and other instructions generated by the model as mentioned below, can be any suitable type of executable instruction. For example, an instruction can be a database query instruction, with the corresponding target task being a database query task. An instruction can also be an instruction to call an application programming interface (API), with the corresponding target task being an API call task. An instruction can also be a data analysis instruction, with the corresponding target task being a data analysis task. Data analysis instructions can be implemented using any suitable type of programming language. It is understood that, in addition to these three types, instructions generated by the model can also be any other suitable type of instruction, and this disclosure does not limit this.

[0049] In box 220, in response to detecting a first error in the execution of a first instruction, the application management platform 110 determines a target error sample that matches the first error from an error sample set, where the error sample in the error sample set corresponds to an instruction execution error.

[0050] In some embodiments, after obtaining the first instruction, the application management platform 110 can provide the first instruction to the corresponding execution platform, execution engine, or execution agent according to the type of the first instruction, so that the execution platform, execution engine, or execution agent can execute the first instruction. For example, if the first instruction is a query instruction for a database, the application management platform 110 can send the first instruction to the corresponding database engine so that the database engine can execute the first instruction to process its query task.

[0051] In some embodiments, the application management platform 110 may receive feedback on the first instruction from a corresponding execution platform, execution engine, or execution agent. The feedback may, for example, indicate whether the execution was successful. If an error occurs during execution (i.e., the first error), the execution result may also indicate, for example, the error type, the cause of the error, etc.

[0052] The error sample set may include multiple error samples. In some embodiments, each error sample may include a corresponding error cause. The error cause may be stored in the error sample set in text form, for example. For each error sample in the error sample set, the application management platform 110 may determine the cause similarity between the first error cause of the first error and the cause of the error sample. The application management platform 110 may determine the cause similarity between the first error cause of the first error and the cause of the error sample using any appropriate method. For example, the application management platform 110 may determine the semantic similarity or text matching degree between the first error cause of the first error and the cause of the error sample, and determine the semantic similarity or text matching degree between the two as the cause similarity between the first error cause of the first error and the cause of the error sample. The application management platform 110 may then select error samples from the error sample set as target error samples based on the cause similarity determined for each error sample. For example, the application management platform 110 may select one or more error samples with the highest corresponding cause similarity as target error samples. The application management platform 110 may also select one or more error samples with corresponding cause similarity higher than a threshold as target error samples.

[0053] In some embodiments, each error sample may further include an error instruction that caused the instruction execution error. Error instructions may be stored in an error sample set associated with the error sample, for example. For each error sample in the error sample set, the application management platform 110 may determine the instruction similarity between a first instruction and the error instructions included in that error sample. The application management platform 110 may determine the instruction similarity between the first instruction and the error instructions included in that error sample using any suitable method; for example, a scoring model may be used to determine the instruction similarity score between the first instruction and the error instructions, where a higher score indicates a higher direct instruction similarity. The application management platform 110 may select error samples from the error sample set as target error samples based on the instruction similarity determined for each error sample. Similarly, the application management platform 110 may select one or more error samples with the highest corresponding instruction similarity or corresponding instruction similarity above a threshold as target error samples.

[0054] In box 230, the application management platform 110 provides the target error sample to the target model to obtain a second instruction for processing the target task. For example, the application management platform 110 may provide user input and the target error sample together to the target model, so that the target model can generate a second instruction for processing the target task based on both.

[0055] In some embodiments, the error samples in the error sample set may further include information for correcting the corresponding instruction execution errors. This information may indicate how to correct the error, how to correctly execute the instruction, etc. Taking a first instruction as a query instruction to the database as an example, if the execution of the first instruction results in a first error, the database feedback may indicate that a first error has occurred, and the first error cause is that the first instruction contains an erroneous character. Then, the information in the error samples obtained by the application management platform 110 for correcting the corresponding instruction execution errors may include "correcting the erroneous character to a correct character or deleting the erroneous character." The target model may, for example, generate a second instruction based on the information in the target error samples for correcting the corresponding instruction execution errors, and the execution of the second instruction will not result in the first error.

[0056] In some embodiments, the error samples in the error sample set may also include correct instruction examples. A correct instruction example may include one or more correct instructions. The target model may, for example, refer to the correct instruction example to generate a second instruction, which can improve the accuracy of the execution of the second instruction and reduce the probability of errors occurring during the execution of the second instruction.

[0057] It is understandable that, similar to the first instruction, the second instruction can also be used to handle target tasks associated with user input. The second instruction may also include database query instructions, application programming interface (API) call instructions, data analysis instructions, and so on.

[0058] In some embodiments, the application management platform 110 can also count instruction execution errors occurring in the instructions generated by the target model according to the error cause during interaction with the target model. For example, if a first error has a first error cause, the application management platform 110 can, in response to the number of instruction execution errors with the first error cause exceeding a threshold number, identify the target error sample matching the first error as a component of the model input of the target model. Thus, the application management platform 110 can directly provide the target model with user input and target error samples, so that the target model can directly generate a correct second instruction. This avoids generating instructions that would result in the first error and directly generates a correct second instruction, improving the efficiency and accuracy of instruction execution.

[0059] The above describes the specific process of obtaining a target error sample from the error sample set and generating a second instruction based on the target error sample when a first error occurs during the execution of the first instruction. The following section combines this with... Figure 3 This describes the process of generating the error sample set. (Reference) Figure 3 , Figure 3 A schematic diagram of example 300 according to some embodiments of the present disclosure is shown.

[0060] In some embodiments, during interaction with the target model, it is possible to detect whether an instruction execution error has occurred in the instructions generated by the target model. In response to the detection of one or more instruction execution errors, an error instruction set is created based on the corresponding instructions that caused the one or more instruction execution errors. An error sample set can also be generated based on the annotation information of the error instructions in the error instruction set. The error instruction set and / or error sample set can be created by the application management platform 110, alternatively or additionally, or it can be from other electronic devices. After other electronic devices have created the error instruction set and / or error sample set, the application management platform 110 can obtain the created error instruction set and / or error sample set from that electronic device.

[0061] For example, such as Figure 3As shown, during the error detection phase, the application management platform 110 can detect (311) instruction execution errors. If one or more instruction execution errors are detected, it collects (312) the one or more instructions that caused the errors. The application management platform 110 can report (313) these one or more instructions to an electronic device used to create an error instruction set, so that the electronic device can create an error instruction set 314 based on the corresponding instructions that caused the one or more instruction execution errors. It can be understood that if the application management platform 110 itself creates the error instruction set, the application management platform 110 can directly create the error instruction set 314 based on the corresponding instructions that caused the one or more instruction execution errors.

[0062] During the manual annotation phase, the electronic device used to create the error sample set can obtain (321) corresponding annotation information for one or more instructions in the error instruction set 314. This annotation information can, for example, be manually input by a professional into the electronic device used to create the error sample set. The annotation information can, for example, indicate information for correcting the corresponding instruction execution error, and / or, examples of correct instructions. The electronic device used to create the error sample set can then generate an error sample set 322 based on the annotation information for the error instructions in the error instruction set. The application management platform 110 can obtain the error sample set 322 from the electronic device used to create the error sample set.

[0063] During the instruction execution phase, the application management platform 110 may, in response to detecting an error in instruction execution (331), identify and recall (322) an error sample 333 that matches the first error from the error sample set 322. The application management platform 110 may provide the error sample 333 to the target model so that the target model can generate (334) new instructions for processing the target task based on the error sample 333.

[0064] In summary, according to the embodiments of this disclosure, when a first error is detected during the execution of a first instruction, a target error sample matching the first error can be determined from the error sample set. Then, using a target model, a correct instruction (i.e., an instruction that will not cause the first error) for processing the target task can be generated based on the target error sample. This enables automatic instruction correction, helping to improve the efficiency and accuracy of instruction execution.

[0065] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes. Figure 4 A schematic structural block diagram of an apparatus 400 for information processing according to some embodiments of the present disclosure is shown. The apparatus 400 may be implemented in or included in an application management platform 110, for example. The various modules / components in the apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0066] As shown in the figure, the device 400 includes a first instruction generation module 410, configured to acquire a first instruction generated by a target model, the first instruction being used to process a target task associated with user input. The device 400 also includes an error sample determination module 420, configured to, in response to detecting a first error in the execution of the first instruction, determine a target error sample matching the first error from an error sample set, the error sample in the error sample set corresponding to an instruction execution error. The device 400 also includes a second instruction acquisition module 430, configured to provide the target error sample to the target model to obtain a second instruction for processing the target task.

[0067] In some embodiments, the error samples in the error sample set include error causes, and the error sample determination module 420 includes: a cause determination module configured to determine, for the error samples in the error sample set, the cause similarity between a first error cause of a first error and the cause of the error sample; and a first sample selection module configured to select an error sample from the error sample set as a target error sample based on the cause similarity determined for each error sample.

[0068] In some embodiments, the error samples in the error sample set include erroneous instructions that cause instruction execution errors, and the error sample determination module 420 includes: a similarity determination module configured to determine, for the error samples in the error sample set, the instruction similarity between a first instruction and the erroneous instructions included in the error sample; and a second sample selection module configured to select an error sample from the error sample set as a target error sample based on the instruction similarity determined for each error sample.

[0069] In some embodiments, the error samples in the error sample set may further include at least one of the following: information for correcting the corresponding instruction execution error, or a correct instruction example.

[0070] In some embodiments, the first error has a first error cause, and the apparatus 400 further includes: a counting module configured to count instruction execution errors occurring in instructions generated by the target model according to the error cause during interaction with the target model; and an identification module configured to identify the target error sample as a component of the model input of the target model in response to the occurrence of instruction execution errors having the first error cause exceeding a threshold number of times.

[0071] In some embodiments, the error sample set is generated by: detecting whether an instruction execution error occurs in the instructions generated by the target model during interaction with the target model; in response to the detection of one or more instruction execution errors, creating an error instruction set based on the corresponding instructions that caused the one or more instruction execution errors; and generating an error sample set based on the annotation information of the error instructions in the error instruction set.

[0072] In some embodiments, the first error is detected by: providing a first instruction to an execution engine for executing the first instruction, based on the type of the first instruction; and receiving feedback from the execution engine regarding the execution of the first instruction, the feedback indicating the first error.

[0073] In some embodiments, the first instruction and the second instruction include at least one of the following types of instructions: a query instruction for a database, a call instruction for an application programming interface, or an analysis instruction for data.

[0074] In some embodiments, the target task includes at least one of the following: analysis of data in a data object, updating of data in a data object, or knowledge question answering for a data object.

[0075] The units and / or modules included in device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units and / or modules in device 400 can be implemented at least partially by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), and so on.

[0076] Figure 5 A block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that... Figure 5 The electronic device 500 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 5 The illustrated electronic device 500 may include or be implemented as Figure 1 Application management platform 110, or Figure 4 Device 400.

[0077] like Figure 5As shown, electronic device 500 is in the form of a general-purpose electronic device. Components of electronic device 500 may include, but are not limited to, one or more processors or processing units 510, memory 520, storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. Processing unit 510 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 520. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 500.

[0078] Electronic device 500 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 500.

[0079] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 5 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0080] Communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functionality of components of electronic device 500 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0081] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0082] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0083] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0084] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0085] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0086] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0087] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An information processing method comprising: obtaining a first instruction generated by a target model based on a user input, the first instruction being for processing a target task associated with the user input, wherein the user input comprises speech or text; in response to detecting that execution of the first instruction occurs a first error, determining a target error sample matching the first error from an error sample set, error samples in the error sample set correspond to instruction execution errors and comprise an error cause, an error instruction causing the instruction execution error, and at least one of: information for correcting the corresponding instruction execution error, or a correct instruction example; and providing the target error sample to the target model to obtain a second instruction for processing the target task, the first instruction, the second instruction, and a type of the error instruction being executable instructions.

2. The method of claim 1, wherein determining a target error sample matching the first error from an error sample set comprises: for error samples in the error sample set, determining a cause similarity between a first error cause of the first error and an error cause of the error sample; and based on the cause similarity determined for each error sample, selecting an error sample from the error sample set as the target error sample.

3. The method of claim 1, wherein determining a target error sample matching the first error from an error sample set comprises: for error samples in the error sample set, determining an instruction similarity between the first instruction and an error instruction comprised by the error sample; and based on the instruction similarity determined for each error sample, selecting an error sample from the error sample set as the target error sample.

4. The method of claim 1, wherein the first error has a first error cause, and the method further comprises: in an interaction with the target model, counting instruction execution errors occurred by instructions generated by the target model by error cause; and in response to a number of instruction execution errors having the first error cause exceeding a threshold number, identifying the target error sample as a component of model input of the target model.

5. The method of claim 1, wherein the error sample set is generated by: in an interaction with the target model, detecting whether instructions generated by the target model occur instruction execution errors; in response to detecting one or more instruction execution errors, creating a set of error instructions based on corresponding instructions causing the one or more instruction execution errors; and based on labeled information of error instructions in the set of error instructions, generating the error sample set.

6. The method of claim 1, wherein the first error is detected by: based on a type of the first instruction, providing the first instruction to an execution engine for executing the first instruction; and receiving feedback of executing the first instruction from the execution engine, the feedback indicating the first error. ​ ​ 7.The method of claim 1, wherein the first instruction and the second instruction comprise at least one of the following types of instructions: a query instruction to a database, a call instruction to an application programming interface, or an analysis instruction for data. 8.The method of claim 1, wherein the target task comprises at least one of the following: an analysis on data in a data object, an update on data in a data object, or a knowledge question answering for a data object. 9.An apparatus for information processing, comprising: a first instruction generation module configured to obtain a first instruction generated by a target model based on a user input, the first instruction being used to process a target task associated with the user input, wherein the user input comprises voice or text; an error sample determination module configured to, in response to detecting that a first error occurs in execution of the first instruction, determine a target error sample matching the first error from an error sample set, the error sample in the error sample set corresponding to an instruction execution error and comprising an error cause, an error instruction causing the instruction execution error, and at least one of the following: information for correcting the corresponding instruction execution error, or a correct instruction example; and a second instruction obtaining module configured to provide the target error sample to the target model to obtain a second instruction for processing the target task, the first instruction, the second instruction, and the error instruction being executable instructions. 10.An electronic device, comprising: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to perform the method according to any one of claims 1 to 8. 11.A computer-readable storage medium having stored thereon a computer program, the computer program being executable by a processor to implement the method according to any one of claims 1 to 8. 12.A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 8. ​

Images