Information processing method and device, equipment and storage medium

Abstract

Embodiments of the present disclosure provide an information processing method, device, equipment and storage medium. The method comprises: in response to receiving a user input, determining a set of structured objects from a plurality of structured objects based on respective semantic relevance of the plurality of structured objects to the user input; determining a target structured object from the set of structured objects based on the user input and configuration information of at least part of the structured objects in the set of structured objects by using a target model; and generating a response to the user input based on the target structured object. Thus, the model can be used to perform two-stage screening of the plurality of structured objects, i.e. coarse screening and fine screening. This helps to reduce information loss and improve the efficiency and accuracy of structured object selection. In addition, the processing capacity of the model for complex information and large amount of information is also enhanced.

Description

TECHNICAL FIELD

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and in particular, to an information processing method, apparatus, device and computer readable storage medium. BACKGROUND

[0002] With the development of information technology, various terminal devices can provide people with various services in work and life, etc. Applications providing services can be deployed in the terminal devices. The terminal devices present corresponding content through the user interface of the application and implement interaction with the user to meet various needs of the user. In some cases, the user can initiate a task processing request in the application. Therefore, how to improve the efficiency and accuracy of task processing is a problem of concern. SUMMARY

[0003] In a first aspect of the present disclosure, an information processing method is provided. The method comprises: in response to receiving a user input, determining a set of structured objects from a plurality of structured objects based on respective semantic relevancies of the plurality of structured objects to the user input; determining a target structured object from the set of structured objects based on the user input and configuration information of at least part of the set of structured objects, by using a target model; and generating a response to the user input based on the target structured object.

[0004] In a second aspect of the present disclosure, an apparatus for information processing is provided. The apparatus comprises: a first object determining module configured to determine a set of structured objects from a plurality of structured objects based on respective semantic relevancies of the plurality of structured objects to a user input, in response to receiving the user input; a second object determining module configured to determine a target structured object from the set of structured objects based on the user input and configuration information of at least part of the set of structured objects, by using a target model; and a response generating module configured to generate a response to the user input based on the target structured object.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device comprises 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, cause the electronic device to perform the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer readable storage medium is provided. The medium has stored thereon a computer program which, when executed by a processor, implements the method of the first aspect.

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

[0008] It should be understood that all the contents described in this section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0009] The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings in which:

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

[0011] Figure 2 A flowchart showing a process of information processing according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A schematic diagram showing an example of information processing according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A schematic block diagram showing 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 DESCRIPTION

[0015] Embodiments of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings. While certain embodiments of the present disclosure will be shown and described, it will be clear to those having ordinary skill in the art that the present disclosure can be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather should be construed as including all embodiments falling within the scope of the present disclosure. It will be understood that the drawings and embodiments herein are for illustrative purposes only and should not be construed as limiting the scope of the present disclosure.

[0016] In the description of embodiments of the present disclosure, the term "includes" and its derivatives are to be construed as open-ended, meaning "including, but not limited to." The term "based on" is to be construed as "based, at least in part, on." The term "one embodiment" or "an embodiment" are to be construed as "at least one embodiment." The term "some embodiments" is to be construed as "at least some embodiments." Other explicit and implicit definitions can 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 can include one or more intervening steps.

[0018] It can be understood that the data involved in the technical solutions of the present disclosure (including but not limited to the data itself, obtaining, using, storing or deleting of the data) should comply with the requirements of relevant laws and regulations and relevant provisions.

[0019] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the type of information involved in the present disclosure, the scope of use, the use scenario, etc. should be informed to the relevant user and the authorization of the relevant user should be obtained by appropriate means according to relevant laws and regulations, wherein the relevant user can include any type of right subject, such as an individual, an enterprise or a group.

[0020] For example, in response to receiving the active request of the user, a prompt information is sent to the relevant user to explicitly prompt the relevant user that the operation requested to be performed will need to obtain and use the information of the relevant user, so that the relevant user can voluntarily choose whether to provide the information to the software or hardware such as electronic device, application program, server or storage medium, etc. performing the operation of the technical solutions of the present disclosure according to the prompt information.

[0021] As an optional but non-limiting implementation manner, in response to receiving the active request of the relevant user, the prompt information can be sent to the relevant user in the form of a pop-up window, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry selection controls for the user to select "agree" or "disagree" to provide information to the electronic device.

[0022] It can be understood that the above notification and user authorization process is only illustrative and does not limit the implementation manner of the present disclosure. Other manners meeting relevant laws and regulations can also be applied to the implementation manner of the present disclosure. The enabling of the digital assistant related function of the embodiment of the present disclosure, the obtained data, the processing and storage manner of the data, etc. should obtain the prior authorization of the user and other right subjects associated with the user, and should comply with relevant laws and regulations, the agreement rules between right subjects.

[0023] As used herein, the term “model” can learn the relationship between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes input and provides a corresponding output by using multiple layers of processing units. The neural network model is an example of a model based on deep learning. In this article, “model” can also be referred to as “machine learning model”, “learning model”, “machine learning network” or “learning network”, which are used interchangeably herein.

[0024] Figure 1 A schematic diagram showing an example environment 100 in which embodiments of the present disclosure can be implemented is shown. The environment 100 involves an application management platform 110, which can support the creation of an application and / or the running of an application. In some embodiments, the part of the application management platform 110 for supporting the creation of an application can also be referred to as an application creation part. In some embodiments, the part of the application management platform 110 for supporting the running of an application can also be referred to as an application running part.

[0025] As shown, the application creation part can provide a creation and publishing environment for an application for a user 105. The user 105 can be referred to as an application creation user, creator. In some embodiments, the application creation part can be a low-code platform that provides a toolset for application creation. The application creation part can support the visual development of various types of applications, so that the developer can skip the manual coding process, speed up the development cycle and cost of the application. The application creation part can support any appropriate platform for the user to develop one or more types of applications, which can include, for example, a platform based on application platform as a service (aPaaS). Such a platform can enable the user to efficiently develop the application, implement application creation, application function adjustment, etc.

[0026] The application creation part can be deployed locally on the terminal device of the user 105 and / or can be supported by a server device. For example, the terminal device of the user 105 can run a client of the application creation part, which can support the user's interaction with the application creation part provided by the server. In the case where the application creation part is run locally on the terminal device of the user, the user 105 can directly interact with the local application creation part using the terminal device. In the case where the application creation part is run on the server device, the server device can implement service provision to the client running on the terminal device based on the communication connection between the terminal device and the server device. The application creation part can present a corresponding page 130 to the user 105 based on the operation of the user 105, to output and / or receive information related to the application creation to / from the user 105.

[0027] In some embodiments, the application creation portion can be associated to a corresponding database in which data or information required by the application creation process supported by the application creation portion is stored. For example, the database can store code and description information corresponding to each functional module used to compose the application, etc. The application creation portion can also perform operations such as calling, adding, deleting, updating, etc. on the functional modules in the database. The database can also store operations executable on different functional blocks. Illustratively, in a scenario in which an application is to be created, the application creation portion can call corresponding functional blocks from the database to build the application.

[0028] In embodiments of the present disclosure, a user 105 can create a target application 120 on the application creation portion as needed and publish the target application 120. The target application 120 can be published to any suitable application running portion as long as the application running portion is capable of supporting the running of the target application 120. After publication, the target application 120 can be used for operation by one or more end users 145. The end users 145 can operate the target application 120 through associated terminal devices 146 and in turn interact with the application management platform 110. The end users 145 can be referred to as end users of the target application 120. In some embodiments, the target application 120 can include or be implemented as a digital assistant 122.

[0029] The digital assistant 122 can be configured to have the capability of intelligent conversation. In the example shown in the figure, the digital assistant 122 can be integrated within the target application 120 as a part of the target application 120 to assist in performing task processing within the target application 120. In other examples, the digital assistant 122 can be configured as an independently running application, such as a web application or other type of application. In such examples, the digital assistant 122 and the target application 120 can be considered as the same application. The digital assistant 122 is provided to assist users in various task processing needs in different applications and scenarios. During interaction with the digital assistant 122, a user inputs an interaction message, and the digital assistant 122 provides a reply message in response to the user input. Generally, the digital assistant 122 is capable of supporting the user to input a question in a natural language manner and perform a task and provide a reply based on understanding of the natural language input and logical reasoning capability.

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

[0031] For each end user 145, the client of the application running part can present an interaction window 142 of the target application 120 or the digital assistant 122 in the client interface, for example, a conversation window with the digital assistant 122. The end user 145 can input a conversation message in the conversation window, and the target application 120 can determine a reply message of the digital assistant 122 based on the created configuration information and present the reply message to the user in the interaction window 142. In some embodiments, depending on the configuration of the target application 120, the interaction message with the target application 120 can include messages in multiple modalities, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and the like.

[0032] Similar to the application creation part, the application running part can be deployed locally at the terminal device of each end user 145 and / or can be supported by the server device. For example, the terminal device of the end user 145 can run a client of the application running part, which can support the user's interaction with the application running part provided by the server. In the case where the application running part is run locally at the terminal device of the user, the end user 145 can directly interact with the local application running part using the terminal device. In the case where the application running part is run at the server device, the server device can implement service provision to the client running at the terminal device based on the communication connection between the terminal device. The application running part can present a corresponding application page to the end user 145 based on the operation of the end user 145 to output and / or receive information related to the use of the application to / from the end user 145.

[0033] In some embodiments, the implementation of at least part of the functions of the target application 120 and / or the implementation of at least part of the functions of the digital assistant 122 in the target application 120 can be implemented based on models. During the creation or running of the target application 120, one or more models 155, for example, the capabilities of the models 155, can be invoked. In the target application 120, the digital assistant 122 can utilize the models 155 to understand the user input and provide a reply to the user based on the output of the models 155.

[0034] During the creation process, the testing of the target application 120 by the application management platform 110 needs to utilize the models 155 to determine that the running result of the target application 120 meets the expectation. During the running process, in response to different operation requests of the user of the target application 120, the application running part can need to utilize the models 155 to determine the response result to the user.

[0035] Although shown as being independent of the application management platform 110, one or more models 155 can run on the application management platform 110, or other remote servers. In some embodiments, the models 155 can be machine learning models, deep learning models, learning models, neural networks, etc. In some embodiments, the models can be based on language models (LMs). Language models can be capable of question answering by learning from a large corpus. The models 155 can also be based on other suitable models.

[0036] The application management platform 110 can run on a suitable electronic device. An electronic device herein can be any type of device with computing capability, including an end device or a server device. An end device can be any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a game device, or any combination thereof, including accessories and peripherals of such devices or any combination thereof. A server device can include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, etc. In some embodiments, the management platform 110 can be implemented based on cloud services.

[0037] It should be understood that the structure and functionality of the environment 100 are described for illustrative purposes only and without implying any limitation on the scope of the present disclosure. For example, although shown as a single user interacting with the application creation portion and a single user interacting with the application running portion, in practice multiple users can access the 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 previously, a user can initiate a task processing request within an application to process information within the application. The application can process the information with the aid of a model. Traditionally, taking an information query as an example, the application can query the information based on a pre-defined query template or based on a user manually matching a query table. This limits the flexibility and efficiency of information querying. Moreover, since the input capacity (which can also be referred to as the model window size) of a target model is limited, the limited input capacity limits the amount of data that the model can process when the target application implements an information processing task that includes a large amount of data with the aid of the model, making the model inefficient in processing information. This can easily lead to information loss, which in turn affects the accuracy of information processing.

[0039] In view of this, in the embodiments of the present disclosure, an improved solution for information processing is provided. In the solution, in response to receiving a user input, a set of structured objects is determined from a plurality of structured objects based on respective semantic relevancies of the plurality of structured objects to the user input. Based on the user input and configuration information of at least part of the set of structured objects, a target structured object is determined from the set of structured objects by using a target model. Based on the target structured object, a response to the user input is generated.

[0040] In this way, the model can be used to perform two-stage screening of the plurality of structured objects, i.e., coarse screening and fine screening. This helps to reduce information loss and improve the efficiency and accuracy of structured object selection. In addition, the processing capacity of the model for complex information and large amount of information is also enhanced.

[0041] Some example embodiments of the present disclosure will be described in detail below with reference to examples of the accompanying drawings.

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

[0043] Figure 2 A flowchart of a process 200 of information processing according to some embodiments of the present disclosure is shown. The process 200 can be implemented in the application management platform 110, for example, can be implemented by the application running part of the application management platform 110. The task processing process shown below is described in conjunction with Figure 1 Figure 2 the application management platform 110.

[0044] At block 210, the application management platform 110 determines a set of structured objects from a plurality of structured objects in response to receiving a user input, based on respective semantic relevancies of the plurality of structured objects to the user input. The process of determining a set of structured objects from a plurality of structured objects can also be regarded as coarse screening of the plurality of structured objects. ​

[0045] The structured object can be any suitable type of object capable of structurally storing or representing information, which can include, but is not limited to, a data table, a database, an API, and the like. The user input can be input from any suitable user, e.g., it can be user input from the user 145. The user input can be any suitable type of user input, e.g., it can be of text type, of voice type, of gesture type, and the like. The application management platform 110 can receive the user input via any suitable manner, e.g., it can receive user input of text type via an input box, receive user input of audio type via a microphone, and the like. The user input can be presented in an interaction window, e.g., the interaction window 142. In some embodiments, where the user input is of non-text type, the application management platform 110 can process the user input to determine text corresponding to the user input. For example, where the user input is of audio type, the application management platform 110 can convert the audio corresponding to the user input to text. The application management platform 110 can subsequently determine the semantic relevance between the user input and the structured objects based on the text corresponding to the user input.

[0046] The application management platform 110 can determine the respective semantic relevance of the plurality of structured objects to the user input in any suitable manner. For example, the application management platform 110 can determine the respective semantic relevance of the plurality of structured objects and the user input by means of a model. In some embodiments, the application management platform 110 can determine the respective semantics of the plurality of structured objects and the user input, and determine the semantic relevance of the plurality of structured objects to the user input by comparing the semantics of the plurality of structured objects to the semantics of the user input.

[0047] Alternatively or additionally, in some embodiments, for a given structured object of the plurality of structured objects, the application management platform 110 can obtain a first encoded representation of the given structured object. The application management platform 110 can determine the first encoded representation of the given structured object in any suitable manner. For example, the application management platform 110 can determine the first encoded representation of the given structured object based on a predetermined rule or algorithm. For another example, the application management platform 110 can determine the first encoded representation of the given structured object by means of any suitable model / encoder.

[0048] In some embodiments, the application management platform 110 can divide the summary information of a given structured object into a plurality of information chunks, and generate the first encoded representation by encoding the plurality of information chunks respectively. The summary information of a structured object can include, for example, the name of the structured object, the description of the structured object, etc. The size of the plurality of information chunks can be predefined, or determined by the application management platform 110 based on the number of texts of the summary information of the given structured object. Similarly, the application management platform 110 can also determine the second encoded representation of the user input.

[0049] The application management platform 110 can then determine the semantic relevance of the given structured object to the user input based on the similarity between the first encoded representation and the second encoded representation of the user input. For example, the application management platform 110 can treat the first encoded representation and the second encoded representation as two vectors respectively, and determine the similarity between the first encoded representation and the second encoded representation by calculating the distance between the two vectors. It can be appreciated that the smaller the distance between the two vectors, the greater the similarity between the corresponding first encoded representation and the second encoded representation, and the higher the semantic relevance of the given structured object to the user input. The application management platform 110 can determine the semantic relevance of a plurality of structured objects to the user input based on such a manner.

[0050] Example embodiments of determining a set of structured objects from a plurality of structured objects based on the respective semantic relevance of the plurality of structured objects to the user input are described below. In some embodiments, the application management platform 110 can determine at least one structured object from the plurality of structured objects whose corresponding semantic relevance is higher than a predetermined threshold as the set of structured objects. Alternatively or additionally, in some embodiments, the application management platform 110 can sort the plurality of structured objects in descending order based on the respective semantic relevance of the plurality of structured objects to the user input. The application management platform 110 can determine at least one structured object from the plurality of structured objects whose ranking is within a predetermined number as the set of structured objects.

[0051] At block 220, the application management platform 110 determines a target structured object from the set of structured objects based on the user input and the configuration information of at least a portion of the set of structured objects using the target model. The process of determining the target structured object from the set of structured objects can also be regarded as a fine screening of the set of structured objects.

[0052] In some embodiments, the configuration information of a given structured object in the plurality of structured objects can include at least one of: a name of the given structured object, a description of the given structured object, one or more fields contained in the given structured object, or respective descriptions of the one or more fields. Taking a structured object as a data table for example, the configuration information of each data table in the plurality of data tables can include a name, a description, contained fields, and descriptions of the contained fields of the data table.

[0053] In some embodiments, the application management platform 110 can rank the set of candidate structured objects based on respective semantic relevancies of the set of structured objects to the user input. For example, the application management platform 110 can rank the set of candidate structured objects in descending order based on respective semantic relevancies of the set of structured objects to the user input. It can be appreciated that a structured object ranked higher in the ranking corresponds to a higher semantic relevance. The application management platform 110 can determine the set of candidate structured objects from the set of structured objects based on an input capacity of the target model and respective input consumptions of the set of structured objects. Here, the input capacity of the target model represents a maximum capacity of data that the target model can receive. Here, the input consumption of a structured object represents an amount of data that, if configured information of the structured object is used as input of the target model, would be consumed by the target model. The application management platform 110 may, for example, determine whether each structured object should be added to the set of candidate structured objects in order based on the ranking.

[0054] Illustratively, the application management platform 110 can determine a first structured object from the set of structured objects to be added to the set of candidate structured objects in order based on the ranking. It is noted that if the first structured object is not the first structured object in the ranking, at least one structured object before the first structured object in the ranking should be added to the set of candidate structured objects. The application management platform 110 can determine a first total consumption of an input consumption of the structured objects already added to the set of candidate structured objects and an input consumption of the first structured object. The first total consumption may, for example, be a sum of the input consumption of the structured objects already added to the set of candidate structured objects and the input consumption of the first structured object.

[0055] The application management platform 110 can compare the first total consumption to the input capacity of the target model to determine whether the first total consumption exceeds the input capacity. If the first total consumption does not exceed the input capacity, the application management platform 110 can add the first structured object to the set of candidate structured objects. If the first total consumption exceeds the input capacity, the application management platform 110 need not add the first structured object to the set of candidate structured objects, and the application management platform 110 can determine that the determination of the set of candidate structured objects is complete.

[0056] For example, if the first structured object is the third structured object in the set of structured objects according to the ordering, then the two structured objects before the first structured object are added to the set of candidate structured objects. The application management platform 110 can determine a first total consumption of input (e.g., which can be a sum of the input consumption of the three structured objects) of the input consumption of the two structured objects before the first structured object and the input consumption of the first structured object. If the input capacity of the target model is 50 and the first total consumption is 40, then the application management platform 110 can determine that the first total consumption does not exceed the input capacity, and thus can add the first structured object to the set of candidate structured objects. The set of candidate structured objects at this point includes the first three structured objects in the set of structured objects.

[0057] Further, for the fourth structured object in the set of structured objects, if it is determined to be the second structured object, the application management platform 110 can determine a second total consumption of input (e.g., which can be a sum of the input consumption of the first four structured objects in the set of structured objects) of the input consumption of the first three structured objects and the input consumption of the second structured object. If the second total consumption is 55, then the application management platform 110 can complete the determination of the set of candidate structured objects in response to the second total consumption exceeding the input capacity. The determined set of candidate structured objects includes the first three structured objects in the set of structured objects.

[0058] After the set of candidate structured objects is determined, the application management platform 110 can select a target structured object from the set of candidate structured objects using the target model based on the user input and configuration information of the candidate structured objects in the set of candidate structured objects. The target model can be a model deployed locally at the application management platform 110 or a model deployed at another electronic device. The target model can be based on any suitable model structure, including but not limited to a Transformer model, a convolutional neural network (CNN), a recurrent neural network (RNN), a deep neural network (DNN), or any suitable model.

[0059] The application management platform 110 may, for example, determine a prompt input for the target model based on the user input and the configuration information of the candidate structured objects in the candidate structured object set. The application management platform 110 may, for example, obtain a prompt template for the target model, and determine the prompt input for the target model by filling the user input and the configuration information of the candidate structured objects in the candidate structured object set into the prompt template. The application management platform 110 may provide the prompt input to the target model. Upon receiving the prompt input, the target model may generate a corresponding model output based on the prompt input. The model output may, for example, indicate which target structured objects are to be selected from the candidate structured object set. The application management platform 110 may obtain the model output from the target model, and select the target structured objects from the candidate structured object set based on the model output. It can be appreciated that the target structured objects may include one or more structured objects.

[0060] The above describes an example process 200 of structured object selection. Below, an example implementation of structured object selection is described with reference to Figure 3 Figure 3 A schematic diagram of an example 300 of information processing according to some embodiments of the present disclosure is shown. The example 300 may include a coarse screening stage 310 and a fine screening stage 320. In the coarse screening stage 310, the application management platform 110 may determine a set of structured objects from a plurality of structured objects. In the fine screening stage 320, the application management platform 110 may determine target structured objects from the set of structured objects. The number of structured objects included in the target structured objects should be less than or equal to the number of structured objects included in the set of structured objects.

[0061] Exemplarily, in the coarse screening stage 310, upon obtaining the plurality of structured objects, the application management platform 110 may determine summary information 311 of each structured object in the plurality of structured objects. The application management platform 110 may determine 312 a first encoded representation of each structured object based on the summary information 311 of the structured object. The application management platform 110 may determine a semantic relevance 313 of each structured object to the user input based on a similarity between the first encoded representation of each structured object and a second encoded representation of the user input. The application management platform 110 may rank 314 the plurality of structured objects, for example, in a descending order, based on the semantic relevance 313 of each structured object to the user input. The application management platform 110 may determine the plurality of structured objects ranked before a predetermined position as the set of structured objects 315.

[0062] ​At the fine screening stage 320, the application management platform 110 can rank the set of candidate structured objects 315 based on the respective semantic relevancy of the set of structured objects to the user input, and in accordance with the ranking, sequentially determine the input consumption of the target structured object and the total consumption of the input consumption of the previous structured objects (321). The application management platform 110 can determine (322) whether the total consumption of the input consumption of the target structured object and the input consumption of the previous structured objects exceeds the input capacity of the model. If the total consumption of the input consumption of the target structured object and the input consumption of the previous structured objects does not exceed the input capacity of the model, the application management platform 110 can add (323) the target structured object to the set of candidate structured objects. If the total consumption of the input consumption of the target structured object and the input consumption of the previous structured objects exceeds the input capacity of the model, the application management platform 110 can determine that the determination of the set of candidate structured objects is completed (i.e., the target structured object is not added to the set of candidate structured objects).

[0063] The application management platform 110 can determine (324) the prompt word input for the target model based on the configuration information of the candidate structured objects in the set of candidate structured objects and the user input. The application management platform 110 can provide (325) the prompt word input to the target model to obtain the model output for the prompt word input from the target model. The application management platform 110 can determine the target structured object 326 from the set of structured objects based on the model output.

[0064] Referring back to Figure 2 At block 230, the application management platform 110 generates a response to the user input based on the target structured object.

[0065] In some embodiments, the application management platform 110 can determine the response to the user input directly based on the target structured object. For example, the application management platform 110 can directly provide the target structured object to the user. Alternatively or additionally, in some embodiments, to improve the delicacy and accuracy of the response, the application management platform 110 can further select at least one field from the plurality of fields based on the respective semantic similarity of the plurality of fields included in the target structured object to the user input. The application management platform 110 can determine a target field from the at least one field using the target model based on the user input and the summary information of the at least one field. The application management platform 110 can further generate the response to the user input based on the target field and the field value under the target field. That is, the application management platform 110 can also perform coarse screening and fine screening on the plurality of fields included in the target structured object. The manner in which the application management platform 110 performs coarse screening and fine screening on the plurality of fields is similar to the manner in which the application management platform 110 performs coarse screening and fine screening on the plurality of structured objects, which will not be described herein again.

[0066] It should be noted that, in some embodiments, to improve the accuracy of fine screening on the plurality of fields, the configuration information of the candidate structured object in the prompt input determined in the fine screening stage on the plurality of fields can be more informative than the configuration information of the candidate structured object in the prompt input determined in the fine screening stage on the plurality of structured objects. For example, if the configuration information of the candidate structured object in the prompt input determined in the fine screening stage on the plurality of structured objects can include the name of the structured object, the description of the structured object, one or more fields contained in the structured object, and a brief description of the one or more fields, the configuration information of the candidate structured object in the prompt input determined in the fine screening stage on the plurality of fields can include the name of the structured object, the description of the structured object, one or more fields contained in the structured object, and a detailed description of the one or more fields.

[0067] In summary, according to embodiments of the present disclosure, two-stage screening of coarse screening and fine screening can be performed on the plurality of structured objects by means of the model. Further, in some embodiments, two-stage screening of coarse screening and fine screening can be performed on the plurality of fields in the target structured object obtained by fine screening by means of the model. This helps to reduce information loss and improve the efficiency and accuracy of information processing. In addition, the processing capacity of the model for complex information and large amount of information is also enhanced.

[0068] Embodiments of the present disclosure also provide a corresponding apparatus for implementing the above method or process. 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, for example, be implemented in or included in the application management platform 110. Various modules / components in the apparatus 400 can be implemented by hardware, software, firmware, or any combination thereof.

[0069] As shown, the apparatus 400 includes a first object determination module 410 configured to determine a set of structured objects from a plurality of structured objects based on respective semantic relevancies of the plurality of structured objects to the user input, in response to receiving the user input. The apparatus 400 further includes a second object determination module 420 configured to determine a target structured object from the set of structured objects based on the user input and configuration information of at least part of the set of structured objects, by means of a target model. The apparatus 400 further includes a response generation module 430 configured to generate a response to the user input based on the target structured object.

[0070] In some embodiments, the second object determining module 420 includes: an ordering module configured to order the set of candidate structured objects based on respective semantic relevancies of the set of structured objects to the user input; an object set determining module configured to determine, from the set of structured objects, a set of candidate structured objects according to the ordering based on the input capacity of the target model and respective input consumptions of the set of structured objects, where the input consumption of a structured object represents an amount of data that configures information of the structured object as input of the target model; and an object selecting module configured to select, from the set of candidate structured objects, a target structured object using the target model based on the user input and configuration information of the candidate structured objects in the set of candidate structured objects.

[0071] In some embodiments, the object set determining module includes: a first determining module configured to determine, from the set of structured objects, a first structured object to be added to the set of candidate structured objects according to the ordering; a second determining module configured to determine whether a first total consumption of the input consumptions of the structured objects already added to the set of candidate structured objects and the input consumption of the first structured object exceeds the input capacity; and an adding module configured to add the first structured object to the set of candidate structured objects in response to the first total consumption not exceeding the input capacity.

[0072] In some embodiments, the apparatus 400 includes: a third determining module configured to determine, from the set of structured objects, a second structured object to be added to the set of candidate structured objects according to the ordering, the second structured object being after the first structured object; a fourth determining module configured to determine whether a second total consumption of the input consumptions of the structured objects already added to the set of candidate structured objects and the input consumption of the second structured object exceeds the input capacity; and a completing module configured to complete the determination of the set of candidate structured objects in response to the second total consumption exceeding the input capacity.

[0073] In some embodiments, the respective semantic relevancies of the plurality of structured objects to the user input are determined as follows: obtaining a first encoded representation of a given structured object in the plurality of structured objects; and determining a semantic relevance of the given structured object to the user input based on a similarity between the first encoded representation and a second encoded representation of the user input.

[0074] In some embodiments, the first encoded representation is generated as follows: dividing summary information of the given structured object into a plurality of information blocks; and generating the first encoded representation by respectively encoding the plurality of information blocks.

[0075] In some embodiments, the response generation module 430 includes: a field selection module configured to select at least one field from the plurality of fields based on a semantic similarity between the plurality of fields included in the target structured object and the user input; a field determination module configured to determine, from the at least one field, a target field based on the user input and profile information of the at least one field, using the target model; and a response determination module configured to generate a response to the user input based on the target field and a field value under the target field.

[0076] In some embodiments, the configuration information of a given structured object in the plurality of structured objects includes at least one of: a name of the given structured object, a description of the given structured object, one or more fields included in the given structured object, or a respective description of the one or more fields.

[0077] The units and / or modules included in the apparatus 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, e.g., machine executable instructions stored on a storage medium. In addition to or alternatively, some or all of the units and / or modules in the apparatus 400 can be implemented at least partially by one or more hardware logic components. As an example and not by way of limitation, example 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), system-on-a-chip (SOCs), complex programmable logic devices (CPLDs), etc.

[0078] Figure 5 A block diagram of an electronic device 500 in which one or more embodiments of the disclosure can be implemented is shown. It should be understood that Figure 5 The electronic device 500 shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 5 The electronic device 500 shown can include or be implemented as Figure 1 the application management platform 110, or Figure 4 the apparatus 400.

[0079] As Figure 5As shown, the electronic device 500 is in the form of a general electronic device. Components of the electronic device 500 can include, but are not limited to, one or more processors or processing units 510, a memory 520, a storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 can be a real or virtual processor and is capable of executing various processing in accordance with programs stored in the memory 520. In a multi-processing system, multiple processing units execute computer-executable instructions in parallel to improve the processing power of the electronic device 500.

[0080] The electronic device 500 typically includes a plurality of computer storage media. Such media can be any available media that is accessible by the electronic device 500 and includes both volatile and non-volatile media, removable and non-removable media. The 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. The storage device 530 can be a removable or non-removable media and can include machine-readable media such as a flash drive, a magnetic disk drive, or any other media that can be used to store information and / or data and that can be accessed by the electronic device 500.

[0081] The electronic device 500 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in Figure 5 disk drives for reading from or writing to a removable, non- volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable, non-volatile optical disk (e.g., a CD-ROM). In these instances, each drive can be connected to the bus (not shown) by one or more data media interfaces. The memory 520 can include a computer program product 525 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0082] The communication unit 540 enables communication with other electronic devices over communication media. Additionally, the functionality of the components of the electronic device 500 can be implemented in a single computing cluster or a plurality of computer machines capable of communicating over a communication connection. As such, the 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 nodes in the networking environment.

[0083] The input device 550 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 560 can be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 500 can also communicate with one or more external devices (not shown), such as storage devices, display devices, etc., one or more devices that enable a user to interact with the electronic device 500, or any devices (e.g., a network card, a modem, etc.) that enable the electronic device 500 to communicate with one or more other electronic devices, as desired via the communication unit 540. Such communication can be carried out via an input / output (I / O) interface (not shown).

[0084] According to an example implementation of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above.

[0085] The computer readable program instructions can also 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 apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0086] The computer readable program instructions can also 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 apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0087] The computer readable program instructions can also 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 apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0088] The computer program product of the present disclosure can be a computer program product, which is a machine-readable medium (media) having instances of the software embodied thereon, such as computer software, firmware, wireless application protocol (WAP), middleware or microcode. For example, a computer program product can be a floppy disk, a CD-ROM, a DVD, a Blu-ray Disc™, a flash drive, a memory stick, a magnetic tape, or a hard disk drive. The machine-readable medium can be a single medium, or multiple media, of the same or different type. The computer program product can be one or more computer program components embodied in medium and / or transmission signals. The computer program product can have one or more computer readable and / or computer executable components embodied in medium and / or transmission signals. The computer program product can be one or more computer readable and / or computer executable components embodied in medium and / or transmission signals. The computer program product can also be at least one or combination of controller(s) with associated computer program component(s), one or more computer program components embodied on medium, and / or one or more computer program components embodied in or of transmission signals. The computer program product can also be at least one computer program component embodied on medium and / or transmission signals. The computer program product can be for taking a set of results and generating a report based on the set of results.

[0089] The foregoing description of implementations has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the various implementations to the precise form disclosed. Many modifications and variations are possible in light of the above teaching. It is intended that the scope of the implementations be limited not by this detailed description, but rather by the claims appended hereto.

Claims

1. An information processing method comprising: in response to receiving a user input, determining a set of structured objects from a plurality of structured objects based on respective semantic relevancies of the plurality of structured objects to the user input; determining a target structured object from the set of structured objects based on a configuration information of at least a portion of the set of structured objects and the user input, by utilizing a target model; and generating a response to the user input based on the target structured object, wherein determining the target structured object from the set of structured objects comprises: ordering the set of structured objects based on respective semantic relevancies of the set of structured objects to the user input; determining a candidate structured object set from the set of structured objects according to the ordering based on an input capacity of the target model and respective input consumptions of the set of structured objects, wherein an input consumption of a structured object represents an amount of data of configuration information of the structured object as input of the target model; and selecting the target structured object from the candidate structured object set based on the user input and configuration information of a candidate structured object in the candidate structured object set, by utilizing the target model.

2. The method of claim 1, wherein determining the candidate structured object set from the set of structured objects according to the ordering comprises: determining a first structured object from the set of structured objects to be added to the candidate structured object set according to the ordering; determining whether a first total consumption of input consumptions of structured objects already added to the candidate structured object set and an input consumption of the first structured object exceeds the input capacity; and in response to the first total consumption not exceeding the input capacity, adding the first structured object to the candidate structured object set.

3. The method of claim 2, further comprising: determining a second structured object from the set of structured objects to be added to the candidate structured object set according to the ordering, the second structured object being subsequent to the first structured object; determining whether a second total consumption of input consumptions of structured objects already added to the candidate structured object set and an input consumption of the second structured object exceeds the input capacity; and in response to the second total consumption exceeding the input capacity, completing the determination of the candidate structured object set.

4. The method of claim 1, wherein the respective semantic relevancies of the plurality of structured objects to the user input are determined as follows: for a given structured object in the plurality of structured objects, obtaining a first encoded representation of the given structured object; and determining a semantic relevance of the given structured object to the user input based on a similarity between the first encoded representation and a second encoded representation of the user input.

5. The method of claim 4, wherein the first encoded representation is generated as follows: dividing summary information of the given structured object into a plurality of information blocks; and ​ ​ ​ The first encoded representation is generated by encoding the plurality of information blocks, respectively. 6.The method of claim 1, wherein generating a response to the user input comprises: selecting at least one field from a plurality of fields contained in the target structured object based on a semantic similarity of the plurality of fields to the user input; determining a target field from the at least one field based on the user input and profile information of the at least one field using the target model; and generating the response to the user input based on the target field and a field value under the target field. 7.The method of claim 1, wherein the configuration information of a given structured object in the plurality of structured objects comprises at least one of: a name of the given structured object, a description of the given structured object, one or more fields contained in the given structured object, or a respective description of the one or more fields. 8.An apparatus for information processing, comprising: a first object determining module configured to determine a set of structured objects from a plurality of structured objects based on a respective semantic relevance of the plurality of structured objects to a user input in response to receiving the user input; a second object determining module configured to determine a target structured object from the set of structured objects based on the user input and configuration information of at least a portion of the set of structured objects using a target model; and a response generating module configured to generate a response to the user input based on the target structured object, wherein the second object determining module is further configured to: rank the set of structured objects based on a respective semantic relevance of the set of structured objects to the user input; determine a candidate structured object set from the set of structured objects according to the ranking based on an input capacity of the target model and a respective input consumption of the set of structured objects, wherein the input consumption of a structured object represents an amount of data of configuration information of the structured object as input to the target model; and select the target structured object from the candidate structured object set based on the user input and configuration information of a candidate structured object in the candidate structured object set using the target model. 9.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 cause the electronic device to perform the method according to any one of claims 1-7. 10.A computer-readable storage medium having stored thereon a computer program executable by a processor to implement the method according to any one of claims 1-7. ​ ​ ​

Images