Information processing method and device, equipment and storage medium
By performing coarse and fine screening on multiple structured objects and using a target model to determine the target structured object, the problem of low information query efficiency in terminal devices is solved, and more efficient and accurate information processing is achieved.
Patent Information
- Application Number
- CN202410667960.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-27
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-05-27
AI Technical Summary
In existing technologies, terminal devices suffer from low information processing efficiency and insufficient accuracy due to limited model input capacity when querying information, which affects the efficiency and accuracy of task processing.
By performing coarse and fine screening on multiple structured objects, the target structured object is determined from the structured objects using the target model, and a response is generated for user input, thereby improving the efficiency and accuracy of information processing.
It reduces information loss, improves the efficiency and accuracy of information processing, and enhances the model's ability to process complex and large amounts of information.
Smart Images

Figure CN119002749A_ABST
Abstract
Description
Technical Field
[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to information processing methods, apparatuses, devices, and computer-readable storage media. Background Art
[0002] With the development of information technology, various terminal devices can provide various services to people in work and life. Applications that provide services can be deployed in terminal devices. Terminal devices present corresponding content and interact with users through the user interface of the application to meet various needs of users. In some cases, users may initiate task processing requests within the application. Therefore, how to improve the efficiency and accuracy of task processing is a problem of concern. Summary of the invention
[0003] In a first aspect of the present disclosure, an information processing method is provided. The method includes: in response to receiving a user input, determining a group of structured objects from a plurality of structured objects based on the corresponding semantic relevances of the plurality of structured objects and the user input; determining a target structured object from the group of structured objects using a target model based on the user input and configuration information of at least a portion of the structured objects in the group of structured objects; and generating a response to the user input based on the target structured object.
[0004] In a second aspect of the present disclosure, there is provided an apparatus for information processing, comprising: a first object determination module, configured to, in response to receiving a user input, determine a group of structured objects from a plurality of structured objects based on corresponding semantic relevances between the plurality of structured objects and the user input; a second object determination module, configured to determine a target structured object from a group of structured objects using a target model based on the user input and configuration information of at least a portion of the structured objects in the group of structured objects; and a response generation 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 includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the electronic device executes the method of the first aspect.
[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the medium, and when the computer program is executed by a processor, the method of the first aspect is implemented.
[0007] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.
[0008] It should be understood that the content described in this section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:
[0010] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;
[0011] Figure 2 A flowchart showing a process of information processing according to some embodiments of the present disclosure;
[0012] Figure 3 A schematic diagram showing an example of information processing according to some embodiments of the present disclosure;
[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 in which one or more embodiments of the present disclosure may be implemented is shown. DETAILED DESCRIPTION
[0015] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0016] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part 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] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.
[0018] It is understandable 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 relevant provisions.
[0019] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scopes of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, 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 prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to software or hardware such as an electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.
[0021] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.
[0022] It is understandable that the above notification and the process of obtaining user authorization are only illustrative and do not limit the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure. The activation of the digital assistant related functions, the acquired data, the processing and storage of the data, etc. in the embodiment of the present disclosure shall obtain the prior authorization of the user and other rights holders associated with the user, and shall comply with the relevant laws and regulations and the agreement rules between the rights holders.
[0023] As used herein, the term "model" can learn the association 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 technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multi-layer processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.
[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 involves an application management platform 110, which can support the creation of applications and / or the running of applications. In some embodiments, the portion of the application management platform 110 that supports the creation of applications can also be referred to as an application creation portion. In some embodiments, the portion of the application management platform 110 that supports the running of applications can also be referred to as an application running portion.
[0025] As shown in the figure, the application creation part can provide a user 105 with an environment for creating and publishing applications. User 105 can be referred to as an application creation user or creator. In some embodiments, the application creation part can be a low-code platform that provides a collection of tools for application creation. The application creation part can support visual development of various types of applications, so that developers can skip the process of manual coding and speed up the development cycle and cost of applications. The application creation part can support any appropriate platform for users to develop one or more types of applications, for example, it can include a platform based on application platform as a service (aPaaS). Such a platform can support users to efficiently develop applications and realize operations such as application creation and application function adjustment.
[0026] The application creation part can be deployed locally on the terminal device of user 105, and / or can be supported by a server-side device. For example, the terminal device of user 105 can run a client of the application creation part, which can support the interaction between the user and the application creation part provided by the server. In the case where the application creation part runs locally on the user's terminal device, the user 105 can directly interact with the local application creation part using the terminal device. In the case where the application creation part runs on the server-side device, the server-side device can, based on the communication connection with the terminal device, implement service provision for the client running in the terminal device. The application creation part can present a corresponding page 130 to the user 105 based on the operation of the user 105, so as to output to the user 105 and / or receive from the user 105 information related to application creation.
[0027] In some embodiments, the application creation part can be associated with a corresponding database, which stores data or information required for the application creation process supported by the application creation part. For example, the database can store the code and description information corresponding to each functional module that constitutes the application. The application creation part can also perform operations such as calling, adding, deleting, and updating the functional modules in the database. The database can also store operations that can be performed on different functional blocks. Exemplarily, in a scenario where an application is to be created, the application creation part can call the corresponding functional blocks from the database to build the application.
[0028] In an embodiment of the present disclosure, a user 105 can create a target application 120 as needed on the application creation part and publish the target application 120. The target application 120 can be published to any appropriate application running part, as long as the application running part can support the operation of the target application 120. After publishing, the target application 120 can be used to be operated by one or more terminal users 145. The terminal user 145 can operate the target application 120 through an associated terminal device 146, and then interact with the application management platform 110. The terminal user 145 can be referred to as the terminal user of the target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.
[0029] The digital assistant 122 can be configured to have the ability of intelligent dialogue. In the example shown in the figure, the digital assistant 122 can be integrated into the target application 120, as part of the target application 120 to assist in the 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 types of applications. In such an example, the digital assistant 122 and the target application 120 can be regarded as the same application. The digital assistant 122 is provided to assist users in various task processing requirements in different applications and scenarios. In the interaction process with the digital assistant 122, the user inputs an interactive message, and the digital assistant 122 provides a reply message in response to the user input. Typically, the digital assistant 122 can support users to input questions in a natural language, and perform tasks and provide replies based on the understanding of natural language input and logical reasoning ability.
[0030] In some embodiments, digital assistant 122 can interact with end user 145 as a contact of end user 145. For example, digital assistant 122 can be implemented in an instant messaging (IM) application. Digital assistant 122 can interact with end user 145 in a single chat session with end user 145. In some embodiments, digital assistant 122 can interact with multiple users in a group chat session including multiple users.
[0031] For each terminal user 145, the client of the application running part can present an interactive window 142 of the target application 120 or the digital assistant 122 in the client interface, such as a conversation window with the digital assistant 122. The terminal user 145 can enter a conversation message in the conversation window, and the target application 120 can determine the reply message of the digital assistant 122 based on the created configuration information and present it to the user in the interactive window 142. In some embodiments, depending on the configuration of the target application 120, the interactive message with the target application 120 may include a message in a multimodal form, such as a text message (e.g., a natural language text), a voice message, an image message, a video message, and the like.
[0032] Similar to the application creation part, the application running part can be deployed locally on the terminal device of each terminal user 145, and / or can be supported by the server device. For example, the terminal device of the terminal user 145 can run a client with the application running part, and the client can support the interaction between the user and the application running part provided by the server. In the case where the application running part runs locally on the user's terminal device, the terminal user 145 can directly use the terminal device to interact with the local application running part. In the case where the application running part runs on the server device, the server device can realize the service supply to the client running in the terminal device based on the communication connection with the terminal device. The application running part can present the corresponding application page to the terminal user 145 based on the operation of the terminal user 145, so as to output and / or receive information related to the use of the application to the terminal 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 the model. During the creation or operation of the target application 120, one or more models 155, such as the capabilities of the model 155, can be called. In the target application 120, the digital assistant 122 can use the model 155 to understand the user input and provide a reply to the user based on the output of the model 155.
[0034] During the creation process, the application management platform 110 needs to use the model 155 to determine whether the operation result of the target application 120 meets expectations when testing the target application 120. During the operation process, in response to different operation requests of the user of the target application 120, the application operation part may need to use the model 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 may run on the application management platform 110, or other remote servers. In some embodiments, the 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). The language model can have question-answering capabilities by learning from a large amount of corpus. The model 155 may also be based on other appropriate models.
[0036] The application management platform 110 can run on appropriate electronic devices. The electronic devices here can be any type of device with computing capabilities, including terminal devices or server devices. The terminal device 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 systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The 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, and the like. 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 exemplary purposes only and do not imply any limitation on the scope of the present disclosure. For example, although a single user interacting with the application creation portion and a single user interacting with the application execution portion are shown, in reality 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 above, users can initiate task processing requests within applications to process information within applications. Applications can process information with the help of models. Traditionally, taking information query as an example, applications can query information based on pre-defined query templates or based on the user's manual matching of query tables. This limits the flexibility and efficiency of information query. In addition, since the input capacity of the target model (also known as the model window size) is limited, when the target application uses the model to implement information processing tasks involving large amounts of data, the limited input capacity limits the amount of data processed by the model, making the model less efficient 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 an embodiment of the present disclosure, an improved information processing scheme is provided. In the scheme, in response to receiving a user input, a group of structured objects is determined from a plurality of structured objects based on the corresponding semantic relevance of the plurality of structured objects to the user input. Based on the user input and configuration information of at least a portion of the structured objects in the group of structured objects, a target structured object is determined from the group of structured objects 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 multiple structured objects: coarse screening and fine screening. This helps reduce information loss and improves the efficiency and accuracy of structured object selection. In addition, it also enhances the model's ability to handle complex information and large amounts of information.
[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 may be implemented on an application management platform, a terminal device on which the application management platform is installed, and / or a server corresponding to the application management platform. In the following examples, 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 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 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 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 the creator, manager or maintainer of the target application 120.
[0043] Figure 2 1 is a flowchart of a process 200 of information processing according to some embodiments of the present disclosure. The process 200 may be implemented in the application management platform 110, for example, by the application running part of the application management platform 110. Figure 1 To describe Figure 2 The task processing process is shown.
[0044] In response to receiving the user input, the application management platform 110 determines a group of structured objects from the plurality of structured objects based on the respective semantic relevances of the plurality of structured objects to the user input in block 210. The process of determining a group of structured objects from the plurality of structured objects can also be regarded as a rough screening of the plurality of structured objects.
[0045] A structured object may be any appropriate type of object capable of storing or representing information in a structured manner, which may include but is not limited to a data table, a database, an API, and the like. User input may be input from any appropriate user, for example, it may be user input from user 145. User input may be any appropriate type of user input, for example, it may be a text type, a voice type, a gesture type, and the like. The application management platform 110 may receive user input via any appropriate manner, for example, it may receive text type user input via an input box, receive audio type user input via a microphone, and the like. The user input may be presented, for example, in an interactive window (e.g., interactive window 142). In some embodiments, in the case where the user input is a non-text type user input, the application management platform 110 may process the user input to determine the text corresponding to the user input. For example, if the user input is an audio type user input, the application management platform 110 may convert the audio corresponding to the user input into text. The application management platform 110 may subsequently determine the semantic relevance between the user input and the structured object based on the text corresponding to the user input.
[0046] The application management platform 110 may determine the corresponding semantic relevance between the plurality of structured objects and the user input in any appropriate manner. For example, the application management platform 110 may determine the semantic relevance between the plurality of structured objects and the user input by means of a model. In some embodiments, the application management platform 110 may determine the semantics of the plurality of structured objects and the user input, and determine the semantic relevance between the plurality of structured objects and the user input by comparing the semantics of the plurality of structured objects with the semantics of the user input.
[0047] Alternatively or additionally, in some embodiments, for a given structured object among multiple structured objects, the application management platform 110 may obtain a first encoded representation of the given structured object. The application management platform 110 may determine the first encoded representation of the given structured object in any appropriate manner. For example, the application management platform 110 may 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 may determine the first encoded representation of the given structured object with the aid of any appropriate model / encoder.
[0048] In some embodiments, the application management platform 110 may divide the summary information of a given structured object into multiple information chunks, and generate a first coded representation by encoding the multiple information chunks respectively. The summary information of the structured object may include, for example, the name of the structured object, the description of the structured object, etc. The sizes of the multiple information chunks here may be predefined, or may be 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 may also determine a second coded representation input by the user.
[0049] The application management platform 110 can further determine the semantic relevance between a given structured object and the user input based on the similarity between the first coded representation and the second coded representation of the user input. For example, the application management platform 110 can regard the first coded representation and the second coded representation as two vectors, respectively, and determine the similarity between the first coded representation and the second coded representation by calculating the distance between the two vectors. It can be understood that the smaller the distance between the two vectors, the greater the similarity between the corresponding first coded representation and the second coded representation, and the higher the semantic relevance between the given structured object and the user input. The application management platform 110 can determine the semantic relevance between multiple structured objects and the user input in this way.
[0050] The following describes an example embodiment of determining a group of structured objects from a plurality of structured objects based on the corresponding semantic relevance of the plurality of structured objects to the user input. In some embodiments, the application management platform 110 may determine at least one structured object among the plurality of structured objects whose corresponding semantic relevance is higher than a predetermined threshold as a group of structured objects. Alternatively or additionally, in some embodiments, the application management platform 110 may sort the plurality of structured objects in descending order based on the corresponding semantic relevance of the plurality of structured objects to the user input. The application management platform 110 may determine at least one structured object among the plurality of structured objects that is ranked first by a predetermined number as a group of structured objects.
[0051] In block 220, the application management platform 110 determines a target structured object from the set of structured objects using the target model based on the user input and configuration information of at least a portion of the structured objects in the set of structured objects. The process of determining the target structured object from the set of structured objects can also be regarded as 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 may include at least one of the following: 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 corresponding descriptions of the one or more fields. Taking the structured object as a data table as an example, the configuration information of each data table in the plurality of data tables may include the name of the data table, the description, the fields contained, and the description of the fields contained.
[0053] In some embodiments, the application management platform 110 may sort a group of candidate structured objects based on the corresponding semantic relevance between the group of structured objects and the user input. For example, the application management platform 110 may sort a group of candidate structured objects in descending order based on the corresponding semantic relevance between the group of structured objects and the user input. It can be understood that the semantic relevance corresponding to the structured object that is closer to the front in the sorting is higher. The application management platform 110 may determine a set of candidate structured objects from a group of structured objects according to the sorting based on the input capacity of the target model and the corresponding input consumption of the group of structured objects. The input capacity of the target model here represents the maximum capacity of the data that the target model can receive. The input consumption of the structured object here represents the amount of data that uses the configuration information of the structured object as the input of the target model. The application management platform 110 may, for example, determine in sequence whether each structured object should be added to the set of candidate structured objects according to the sorting.
[0054] Exemplarily, the application management platform 110 may determine the first structured object to be added to the candidate structured object set from a group of structured objects according to the sorting. It should be noted that if the first structured object is not the first structured object in the sorting, at least one structured object before the first structured object should be added to the candidate structured object set. The application management platform 110 may determine a first total consumption (token) of the input consumption of the structured objects that have been added to the candidate structured object set and the input consumption of the first structured object. The first total consumption may be, for example, the sum of the input consumption of the structured objects that have been added to the candidate structured object set and the input consumption of the first structured object.
[0055] The application management platform 110 may compare the first total consumption with 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 may add the first structured object to the candidate structured object set. If the first total consumption exceeds the input capacity, the application management platform 110 does not need to add the first structured object to the candidate structured object set, and the application management platform 110 may determine that the determination of the candidate structured object set is completed.
[0056] Exemplarily, if the first structured object is ranked as the third structured object in a group of structured objects, the two structured objects before the first structured object are both added to the candidate structured object set. The application management platform 110 can determine the first total consumption of the input consumption of the first two structured objects and the input consumption of the first structured object (for example, it can be the sum of the input consumption of the three structured objects). If the input capacity of the target model is 50 and the first total consumption is 40, the application management platform 110 can determine that the first total consumption does not exceed the input capacity, and then the first structured object can be added to the candidate structured object set. At this time, the candidate structured object set includes the first three structured objects in a group of structured objects.
[0057] Further, for the fourth structured object in a group of structured objects, if it is determined to be a second structured object, the application management platform 110 may determine a second total consumption of the input consumption of the first three structured objects and the input consumption of the second structured object (for example, it may be the sum of the input consumption of the first four structured objects in the group of structured objects). If the second total consumption is 55, the application management platform 110 may complete the determination of the candidate structured object set in response to the second total consumption exceeding the input capacity. The determined candidate structured object set includes the first three structured objects in the group of structured objects.
[0058] After the candidate structured object set is determined, the application management platform 110 can select a target structured object from the candidate structured object set based on the user input and the configuration information of the candidate structured objects in the candidate structured object set using the target model. This target model can be a model deployed locally on the application management platform 110, or a model deployed at other electronic devices. The target model can be based on any appropriate model structure, including but not limited to any appropriate model such as a Transformer model, a convolutional neural network (CNN), a recurrent neural network (RNN), a deep neural network (DNN), etc.
[0059] The application management platform 110 can, for example, determine a prompt input for the target model based on user input and configuration information of candidate structured objects in the candidate structured object set. The application management platform 110 can, for example, obtain a prompt template for the target model, and determine the prompt input for the target model by filling the prompt template with the user input and configuration information of candidate structured objects in the candidate structured object set. The application management platform 110 can provide the prompt input to the target model. After receiving the prompt input, the target model can generate a corresponding model output based on the prompt input. The model output can, for example, indicate which target structured objects are selected from the candidate structured object set. The application management platform 110 can obtain the model output from the target model, and select the target structured object from the candidate structured object set based on the model output. It can be understood that the target structured object can include one or more structured objects.
[0060] The above describes an example process 200 for structured object selection. Figure 3 To describe an example implementation of structured object selection. 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 rough screening stage 310 and a fine screening stage 320. In the rough screening stage 310, the application management platform 110 may determine a group of structured objects from a plurality of structured objects. In the fine screening stage 320, the application management platform 110 may determine a target structured object from a group of structured objects. The number of structured objects included in the target structured object should be less than or equal to the number of structured objects included in the group of structured objects.
[0061] Exemplarily, in the rough screening stage 310, after the application management platform 110 obtains multiple structured objects, it can determine the summary information 311 of each structured object in the multiple structured objects. The application management platform 110 can determine (312) the first coding representation of each structured object based on the summary information 311 of the structured object. The application management platform 110 can determine the semantic relevance 313 of each structured object to the user input based on the similarity between the first coding representation of each structured object and the second coding representation of the user input. The application management platform 110 can sort (314) the multiple structured objects based on the semantic relevance 313 of each structured object to the user input, for example, sorting the multiple structured objects in descending order. The application management platform 110 can determine the multiple structured objects that are ranked before a predetermined ranking as a group of structured objects 315.
[0062] In the fine screening stage 320, the application management platform 110 can sort a set of candidate structured objects 315 based on the corresponding semantic relevance between the set of structured objects and the user input, and determine the total consumption of the input consumption of the target structured object and the input consumption of the previous structured object in turn based on the sorting (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 object 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 object does not exceed the input capacity of the model, the application management platform 110 can add (323) the target structured object to the candidate structured object set. If the total consumption of the input consumption of the target structured object and the input consumption of the previous structured object exceeds the input capacity of the model, the application management platform 110 can determine that the determination of the candidate structured object set has been completed (that is, the target structured object is not added to the candidate structured object set).
[0063] The application management platform 110 may determine (324) a prompt word input for a target model based on configuration information of a candidate structured object in the candidate structured object set and user input. The application management platform 110 may provide (325) the prompt word input to the target model to obtain a model output for the prompt word input from the target model. The application management platform 110 may determine 326 a target structured object from a set of structured objects based on the model output.
[0064] Return to reference Figure 2 In 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 may directly determine a response to the user input based on the target structured object. For example, the application management platform 110 may directly provide the target structured object to the user. Alternatively or additionally, in some embodiments, to improve the precision and accuracy of the response, the application management platform 110 may also select at least one field from multiple fields based on the corresponding semantic similarity between the multiple fields contained in the target structured object and the user input. The application management platform 110 may determine the target field from at least one field based on the user input and the summary information of at least one field, using the target model. The application management platform 110 may then generate a 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 may also perform rough screening and fine screening on the multiple fields included in the target structured object. The manner in which the application management platform 110 performs rough screening and fine screening on multiple fields is similar to the manner in which the application management platform 110 performs rough screening and fine screening on multiple structured objects, and will not be repeated here.
[0066] It should be noted that, in some embodiments, in order to improve the accuracy of fine screening of multiple fields, the configuration information of the candidate structured objects in the prompt word input determined by the application management platform 110 in the fine screening stage of multiple fields can be more information-rich than the configuration information of the candidate structured objects in the prompt word input determined in the fine screening stage of multiple structured objects. For example, if the configuration information of the candidate structured objects in the prompt word input determined in the fine screening stage of multiple structured objects can include the name of the structured object, the description of the structured object, one or more fields included in the structured object, and a brief description of one or more fields, then the configuration information of the candidate structured objects in the prompt word input determined in the fine screening stage of multiple fields can include the name of the structured object, the description of the structured object, one or more fields included in the structured object, and a detailed description of one or more fields.
[0067] In summary, according to the embodiments of the present disclosure, the model can be used to perform two-stage screening of multiple structured objects, namely, rough screening and fine screening. Further, in some embodiments, the model can be used to perform two-stage screening of multiple fields in the target structured object obtained by fine screening. This helps to reduce information loss and improve the efficiency and accuracy of information processing. In addition, the model's ability to process complex information and large amounts of data is also enhanced.
[0068] The embodiments of the present disclosure also provide corresponding devices 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 the application management platform 110, for example. Each module / component in the apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.
[0069] As shown in the figure, the device 400 includes a first object determination module 410, which is configured to determine a group of structured objects from a plurality of structured objects based on the corresponding semantic relevance of the plurality of structured objects to the user input in response to receiving the user input. The device 400 also includes a second object determination module 420, which is configured to determine a target structured object from a group of structured objects using a target model based on the user input and configuration information of at least a portion of the structured objects in the group of structured objects. The device 400 also includes a response generation module 430, which is configured to generate a response to the user input based on the target structured object.
[0070] In some embodiments, the second object determination module 420 includes: a sorting module, configured to sort a group of candidate structured objects based on the corresponding semantic relevance between the group of structured objects and the user input; and an object set determination module, configured to determine a set of candidate structured objects from a group of structured objects according to the sorting based on the input capacity of the target model and the corresponding input consumption of the group of structured objects, wherein the input consumption of the structured object represents the amount of data using the configuration information of the structured object as the input of the target model; and an object selection module, configured to select a target structured object from the candidate structured object set using the target model based on the user input and the configuration information of the candidate structured objects in the candidate structured object set.
[0071] In some embodiments, the object set determination module includes: a first determination module, configured to determine, from a group of structured objects, a first structured object to be added to the candidate structured object set according to a sort; a second determination module, configured to determine whether a first total consumption of input consumption of structured objects added to the candidate structured object set and an input consumption of the first structured object exceeds the input capacity; and an adding module, configured to add the first structured object to the candidate structured object set in response to the first total consumption not exceeding the input capacity.
[0072] In some embodiments, the device 400 includes: a third determination module, configured to determine, from a group of structured objects, a second structured object to be added to the candidate structured object set according to the sort, the second structured object being after the first structured object; a fourth determination module, configured to determine whether a second total consumption of the input consumption of the structured objects added to the candidate structured object set and the input consumption of the second structured object exceeds the input capacity; and a completion module, configured to complete the determination of the candidate structured object set in response to the second total consumption exceeding the input capacity.
[0073] In some embodiments, the corresponding semantic relevance of multiple structured objects to user input is determined as follows: for a given structured object among the multiple structured objects, a first encoded representation of the given structured object is obtained; and based on the similarity between the first encoded representation and a second encoded representation of the user input, the semantic relevance of the given structured object to the user input is determined.
[0074] In some embodiments, the first coded representation is generated by: dividing summary information of a given structured object into a plurality of information blocks; and generating the first coded representation by encoding the plurality of information blocks respectively.
[0075] In some embodiments, the response generation module 430 includes: a field selection module, configured to select at least one field from multiple fields based on the corresponding semantic similarities between multiple fields contained in the target structured object and the user input; a field determination module, configured to determine a target field from at least one field based on the user input and summary information of at least one field using a target model; and a response determination module, configured to generate a response to the user input based on the target field and the field value under the target field.
[0076] In some embodiments, the configuration information of a given structured object among the multiple structured objects includes at least one of the following: 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 corresponding description of the one or more fields.
[0077] The units and / or modules included in the 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 the device 400 can be implemented at least in part by one or more hardware logic components. As an 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 the like.
[0078] Figure 5 1 shows a block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 5 The electronic device 500 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 5 The electronic device 500 shown may include or be implemented as Figure 1 application management platform 110, or Figure 4 Device 400.
[0079] like Figure 5As shown, the electronic device 500 is in the form of a general electronic device. The components of the electronic device 500 may 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 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 520. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 500.
[0080] The electronic device 500 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 520 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 530 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 500.
[0081] The electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 5 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 520 may include a computer program product 525 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.
[0082] The communication unit 540 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 500 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 500 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.
[0083] The input device 550 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 560 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 500 may also communicate with one or more external devices (not shown) through the communication unit 540 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 500, or communicate with any device that allows the electronic device 500 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).
[0084] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.
[0085] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.
[0086] 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 device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0087] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0088] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.
[0089] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.
Claims
1. An information processing method, comprising: In response to receiving a user input, determining a set of structured objects from the plurality of structured objects based on respective semantic relevances of the plurality of structured objects to the user input; Determining a target structured object from the set of structured objects using a target model based on the user input and configuration information of at least a portion of the structured objects in the set of structured objects; as well as A response to the user input is generated based on the target structured object.
2. The method according to claim 1, wherein determining a target structured object from the set of structured objects comprises: sorting the set of candidate structured objects based on respective semantic relevances of the set of structured objects to the user input; as well as determining a candidate set of structured objects from the set of structured objects according to the ranking based on the input capacity of the target model and the corresponding input consumption of the set of structured objects, wherein the input consumption of the structured object represents the amount of data that takes the configuration information of the structured object as the input of the target model; as well as Based on the user input and configuration information of candidate structured objects in the candidate structured object set, the target structured object is selected from the candidate structured object set using the object model.
3. The method according to claim 2, wherein determining a candidate set of structured objects from the set of structured objects according to the ranking comprises: According to the ranking, determining a first structured object to be added to the candidate structured object set from the group of structured objects; determining whether a first total consumption of input consumption of structured objects added to the candidate structured object set and the input consumption of the first structured object exceeds the input capacity; as well as In response to the first total consumption not exceeding the input capacity, the first structured object is added to the set of candidate structured objects.
4. The method according to claim 2 or 3, further comprising: According to the sorting, determining a second structured object to be added to the candidate structured object set from the group of structured objects, the second structured object being after the first structured object; determining whether a second total consumption of the input consumption of the structured objects added to the candidate structured object set and the input consumption of the second structured object exceeds the input capacity; as well as In response to the second total consumption exceeding the input capacity, determining the candidate set of structured objects is completed.
5. The method of claim 1 , wherein the respective semantic relevance of the plurality of structured objects to the user input is determined as follows: For a given structured object among the plurality of structured objects, obtaining a first encoded representation of the given structured object; and A semantic relevance of the given structured object to the user input is determined based on a similarity between the first encoded representation and a second encoded representation of the user input.
6. The method of claim 5, wherein the first encoded representation is generated as follows: Dividing the summary information of the given structured object into a plurality of information blocks; and The first coded representation is generated by encoding the plurality of information blocks respectively.
7. The method of claim 1 , wherein generating a response to the user input comprises: Selecting at least one field from the multiple fields based on the corresponding semantic similarities between the multiple fields included in the target structured object and the user input; Determine a target field from the at least one field using the target model based on the user input and summary information of the at least one field; as well as The response to the user input is generated based on the target field and field values under the target field.
8. The method according to claim 1, wherein the configuration information of a given structured object in the plurality of structured objects comprises at least one of the following: the 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 corresponding description of the one or more fields.
9. An apparatus for information processing, comprising: a first object determination module configured to, in response to receiving a user input, determine a group of structured objects from the plurality of structured objects based on respective semantic relevances of the plurality of structured objects to the user input; a second object determination module configured to determine a target structured object from the group of structured objects using a target model based on the user input and configuration information of at least a portion of the structured objects in the group of structured objects; as well as The response generation module is configured to generate a response to the user input based on the target structured object.
10. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 8 when executed by the at least one processing unit.
11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 8.
Citation Information
Patent Citations
Method and system for realizing customer service matching by using multi-modal algorithm
CN116821430A
Building information model intelligent extraction method and system based on large language model
CN117332069A
Interaction method and device, equipment and storage medium
CN117519528A
Method and system for realizing e-commerce commodity information interaction by using large language model
CN117592489A
Large model semantic interaction engine and dynamic analysis method of composite intention text
CN117669590A
Cited By
Information processing method and apparatus, device and storage medium
WO2025246492A1
