CN118839768A - Information processing method, apparatus, device and storage medium - Google Patents
Information processing method, apparatus, device and storage medium Download PDFInfo
- Publication number
- CN118839768A CN118839768A CN202410851923.1A CN202410851923A CN118839768A CN 118839768 A CN118839768 A CN 118839768A CN 202410851923 A CN202410851923 A CN 202410851923A CN 118839768 A CN118839768 A CN 118839768A
- Authority
- CN
- China
- Prior art keywords
- processing
- target data
- data
- target
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/041—Abduction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Stored Programmes (AREA)
Abstract
The embodiment of the disclosure provides an information processing method, an information processing device and a storage medium. The method comprises the following steps: responsive to receiving the user input, obtaining target data indicated by the user input; generating at least one processing instruction for the target data using the target model based on source information about a source of the target data; respectively acquiring at least one processing result by executing at least one processing instruction on the target data; and generating an analysis result for the target data as a response to the user input using the target model based on the at least one processing result. Thus, processing instructions for data can be generated by means of the model, and analysis results of the data can be determined based on the processing results of the data instructions by means of the model. This helps to improve the efficiency and accuracy of information processing.
Description
Technical Field
Example embodiments of the present disclosure relate generally to the field of computers and, more particularly, relate to information processing methods, apparatuses, devices, and computer-readable storage media.
Background
With the development of information technology, various terminal devices can provide various services to people in terms of work and life, etc. The terminal device may have an application deployed therein that provides a service. The terminal equipment presents corresponding content through the user interface of the application, realizes interaction with the user and meets various requirements of the user. In some cases, a user may initiate an information processing request within an application. Therefore, how to improve the efficiency of information processing is a concern.
Disclosure of Invention
In a first aspect of the present disclosure, an information processing method is provided. The method comprises the following steps: responsive to receiving the user input, obtaining target data indicated by the user input; generating at least one processing instruction for the target data using the target model based on source information about a source of the target data; respectively acquiring at least one processing result by executing at least one processing instruction on the target data; and generating an analysis result for the target data as a response to the user input using the target model based on the at least one processing result.
In a second aspect of the present disclosure, there is provided an apparatus for information processing, comprising: a target data acquisition module configured to acquire target data indicated by user input in response to receiving the user input; a processing instruction generation module configured to generate at least one processing instruction for the target data using the target model based on source information about a source of the target data; a processing result acquisition module configured to acquire at least one processing result by executing at least one processing instruction on the target data, respectively; and an analysis result generation module configured to generate an analysis result for the target data as a response to the user input using the target model based on the at least one processing result.
In a third aspect of the present disclosure, an electronic device is provided. The apparatus 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 at least one processing unit, cause the electronic device to perform the method of the first aspect.
In a fourth aspect of the present disclosure, a computer-readable storage medium is provided. A medium has stored thereon a computer program which, when executed by a processor, implements the method of the first aspect.
According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method according to the first aspect of the present disclosure.
It should be understood that what is described in this section is not intended to limit the key features or essential 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 apparent from the following description.
Drawings
The above and other features, advantages and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, wherein like or similar reference numerals denote like or similar elements, in which:
FIG. 1 illustrates a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;
FIG. 2 illustrates a flow chart of a process of information processing according to some embodiments of the present disclosure;
FIG. 3 illustrates a schematic diagram of an example of information processing according to some embodiments of the present disclosure;
FIG. 4 illustrates a schematic block diagram of an apparatus for information processing according to some embodiments of the present disclosure;
fig. 5 illustrates a block diagram of an electronic device in which one or more embodiments of the disclosure may be implemented.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been illustrated in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather, these embodiments are provided so that this disclosure will be more thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
In describing embodiments of the present disclosure, the term "comprising" and its like should be taken to be open-ended, i.e., 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 are also possible below.
In this context, unless explicitly stated otherwise, performing a step "in response to a" does not mean that the step is performed immediately after "a", but may include one or more intermediate steps.
It will be appreciated that the data (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) involved in the present technical solution should comply with the corresponding legal regulations and the requirements of the relevant regulations.
It will be appreciated that prior to using the technical solutions disclosed in the embodiments of the present disclosure, the relevant users, which may include any type of rights subjects, such as individuals, enterprises, groups, etc., should be informed and authorized by appropriate means of the types of information, usage ranges, usage scenarios, etc. involved in the present disclosure according to relevant legal regulations.
For example, in response to receiving an active request from a user, 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 information to the relevant user, so that the relevant user may autonomously select whether to provide information to software or hardware such as an electronic device, an application program, a server, or a storage medium that performs the operation of the technical solution of the present disclosure according to the prompt information.
As an alternative but non-limiting implementation manner, in response to receiving an active request from a relevant user, the prompt information may be sent to the relevant user, for example, in a popup window, where the prompt information may be presented in a text manner. In addition, a selection control for the user to select to provide information to the electronic device in a 'consent' or 'disagreement' manner can be carried in the popup window.
It will be appreciated that the above-described notification and user authorization process is merely illustrative and not limiting of the implementations of the present disclosure, and that other ways of satisfying relevant legal regulations may be applied to the implementations of the present disclosure. The starting of the related functions of the digital assistant, the acquired data, the processing and storage modes of the data and the like of the embodiment of the disclosure should all obtain the advanced authorization of the user and other rights subjects associated with the user, and should conform to the relevant legal regulations and the agreement rules among the rights subjects.
As used herein, the term "model" may learn the association between the respective inputs and outputs from training data so that, for a given input, a corresponding output may be generated after training is completed. The generation of the model may be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs through the use of multiple layers of processing units. The neural network model is one example of a deep learning-based model. The "model" may also be referred to herein as a "machine learning model," "machine learning network," or "learning network," which terms are used interchangeably herein.
FIG. 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure may be implemented. The environment 100 relates to an application management platform 110 that may support the creation of applications and/or the running of applications. In some embodiments, the portion of the application management platform 110 that is used to support application creation may also be referred to as an application creation portion. In some embodiments, the portion of the application management platform 110 that is used to support application execution may also be referred to as an application execution portion.
As shown, the application creation section may provide the user 105 with a creation and release environment for the application. The user 105 may be referred to as an application creation user, creator. In some embodiments, the application creation portion may be a low code platform that provides a collection of tools for application creation. The application creation part can support visual development of various applications, so that a developer can skip the process of manual coding, and the development period and cost of the applications are quickened. The application creation portion may support any suitable platform for a user to develop one or more types of applications, and may include, for example, an application platform-based, i.e., service (aPaaS) platform. The platform can support the user to develop the application with high efficiency, and realize the operations of application creation, application function adjustment and the like.
The application creation portion may be deployed locally to the terminal device of the user 105 and/or may be supported by a server device. For example, a terminal device of user 105 may run a client with an application creation portion that may support user interactions with the application creation portion provided by the server. In the case where the application creation section runs locally at the user's terminal device, the user 105 can interact directly with the local application creation section using the terminal device. In the case where the application creation section operates on the server side device, the server side device may realize service provision to the client side operating in the terminal device based on the communication connection with the terminal device. The application creation section may present the corresponding page 130 to the user 105 based on the operation of the user 105 to output to the user 105 and/or receive information related to application creation from the user 105.
In some embodiments, the application creation section may be associated with a corresponding database in which data or information required for the application creation process supported by the application creation section is stored. For example, the database may store codes and description information and the like corresponding to the respective functional modules constituting the application. The application creation section may also perform operations such as calling, adding, deleting, updating, etc. on the function modules in the database. The database may also store operations that are performed on different functional blocks. For example, in a scenario in which an application is to be created, the application creation section may call corresponding function blocks from the database to build the application.
In an embodiment of the present disclosure, the user 105 may create the target application 120 on the application creation section as needed and issue the target application 120. The target application 120 may 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 release, the target application 120 may be available for operation by one or more end users 145. The end user 145 may operate the target application 120 through an associated terminal device 146 and in turn interact with the application management platform 110. End user 145 may be referred to as an end user of target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.
The digital assistant 122 may be configured with intelligent dialog capabilities. In the example shown in the figures, the digital assistant 122 may be integrated within the target application 120 as part of the target application 120 to assist in performing task processing within the target application 120. In other examples, digital assistant 122 may be configured as a stand-alone application, such as a web application or other type of application. In such an example, the digital assistant 122 may be considered the same application as the target application 120. The digital assistant 122 is provided to assist the user in various task processing needs for different applications, scenarios. During interaction with the digital assistant 122, the user enters an interaction message, and the digital assistant 122 provides a reply message in response to the user input. In general, the digital assistant 122 is capable of supporting a user to input questions in natural language and perform tasks and provide replies based on understanding and logical reasoning capabilities of the natural language input.
In some embodiments, digital assistant 122 may interact with end user 145 as a contact. For example, digital assistant 122 may be implemented in an Instant Messaging (IM) application. Digital assistant 122 may interact with end user 145 in a single chat session with end user 145. In some embodiments, digital assistant 122 may interact with multiple users in a group chat session that includes multiple users.
For each end user 145, the client of the application running portion may present an interactive window 142 of the target application 120 or digital assistant 122, such as a session window with the digital assistant 122, in a client interface. End user 145 may enter a session message in the session window and target application 120 may determine a reply message to digital assistant 122 based on the created configuration information and present to the user in interactive window 142. In some embodiments, depending on the configuration of the target application 120, the interaction message with the target application 120 may include a multimodal form of message, such as a text message (e.g., natural language text), a voice message, an image message, a video message, and so forth.
Similar to the application creation section, the application execution section may be deployed locally to the terminal device of each end user 145 and/or may be supported by a server device. For example, the terminal device of end user 145 may run a client having an application running portion that may support user interaction with the application running portion provided by the server. In the case where the application run-time portion is running locally at the user's terminal device, the end user 145 may interact directly with the local application run-time portion using the terminal device. In the case where the application running section runs on the server device, the server device may realize service provision to the client running in the terminal device based on the communication connection with the terminal device. The application execution portion may present the corresponding application page to the end user 145 based on the operation of the end user 145 to output to the end user 145 and/or receive information related to application usage from the end user 145.
In some embodiments, the implementation of at least a portion of the functionality of the target application 120, and/or the implementation of at least a portion of the functionality of the digital assistant 122 in the target application 120, may be model-based. One or more models 155, such as the capabilities of the models 155, may be invoked during creation or execution of the target application 120. In target application 120, digital assistant 122 may utilize model 155 to understand user input and provide a reply to the user based on the output of model 155.
In the creation process, testing of the target application 120 by the application management platform 110 requires the use of the model 155 to determine that the results of the operation of the target application 120 are expected. During execution, the application execution portion may need to utilize model 155 to determine a response result to a user in response to different operation requests by the user of target application 120.
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 neural network, or the like. In some embodiments, the model may be based on a Language Model (LM). The language model can have question-answering capability by learning from a large number of corpora. Model 155 may also be based on other suitable models.
The application management platform 110 may run on an appropriate electronic device. The electronic device herein may be any type of device having computing capabilities, including a terminal device or a server device. The terminal device may be any type of mobile terminal, fixed terminal, or portable terminal, including a mobile handset, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, media computer, multimedia tablet, personal Communication System (PCS) device, personal navigation device, personal Digital Assistant (PDA), audio/video player, digital camera/camcorder, positioning device, television receiver, radio broadcast receiver, electronic book device, game device, or any combination of the preceding, including accessories and peripherals for these devices, or any combination thereof. The server devices may include, for example, computing systems/servers, such as mainframes, edge computing nodes, computing devices in a cloud environment, and so forth. In some embodiments, the management platform 110 may be implemented based on cloud services.
It should be understood that the structure and function of environment 100 are described for illustrative purposes only and are not meant to suggest any limitation as to the scope of the disclosure. For example, while a single user interacting with the application creation section and a single user interacting with the application execution section are illustrated, in practice multiple users may access the application management platform 110 to each create a digital assistant, and each digital assistant may be used to interact with multiple users.
As mentioned previously, a user may initiate a task processing request within an application to process information within the application. Traditionally, applications may implement data analysis by means of an analysis framework, e.g. providing data insight. However, when the data volume is large, it is difficult to apply the data analysis result which is convenient and quick and has accurate determination. To improve accuracy of data analysis, data analysis may also be performed manually, which may increase labor costs for data analysis. Manually performing data analysis may further reduce the efficiency of data analysis.
In view of this, in the embodiments of the present disclosure, an improvement scheme of information processing is provided. In this scheme, in response to receiving a user input, target data indicated by the user input is acquired. At least one processing instruction for the target data is generated using the target model based on source information related to a source of the target data. And respectively acquiring at least one processing result by executing at least one processing instruction on the target data. Based on at least one processing result, an analysis result for the target data is generated as a response to the user input using the target model.
In this way, processing instructions for data can be generated by means of the model, and the analysis result of the data can be determined based on the processing result of the data instructions by means of the model. The specific data processing may not be performed by the model, but may be performed by the instruction execution engine. Thus, data processing that the model may not be good at can be stripped from the model. This helps to improve the efficiency and accuracy of information processing.
Some example embodiments of the present disclosure will be described in detail below with reference to examples of the accompanying drawings.
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 examples below, the description is from the perspective of an application management platform, such as application management platform 110 shown in FIG. 1, for discussion purposes. The user interface presented by the application management platform 110 may be presented via the terminal device of the user 145 and the application management platform 110 may receive user input via the terminal device of the user 145. In some embodiments of the present disclosure, the user 145 is an end user of the target application 120. It should be appreciated that the user interface presented by the application management platform 110 may also be presented via the terminal device of the user 105, and that the application management platform 110 may 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.
Fig. 2 illustrates a flow chart of a process 200 of information processing according to some embodiments of the present disclosure. The process 200 may be implemented at the application management platform 110, for example, by an application running portion of the application management platform 110. The task processing procedure shown in fig. 2 is described below in conjunction with fig. 1.
At block 210, the application management platform 110, in response to receiving the user input, obtains target data indicated by the user input.
The user input may be input from any suitable user, for example, it may be user input from user 145. The user input may be any suitable type of user input, for example, may be a text type, a voice type, a gesture type, and so forth. The application management platform 110 may receive user input via any suitable means, e.g., may receive user input of text type via an input box, audio type via a microphone, and so forth. The user input may be presented, for example, in an interactive window (e.g., interactive window 142). In some embodiments, 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 to which the user input corresponds. For example, if the user input is a user input of an audio type, the application management platform 110 may convert the audio corresponding to the user input into text.
The target data may include raw data in the data object. The data object may be, for example, a structured object. The structured objects may be any suitable type of object capable of structurally storing or representing information, which may include, but is not limited to, a data table, a database, and the like. For example, the target data may include raw data in a data table. The target data may also include data determined based on the raw data. For example, the target data may include data calculated from the raw data.
In some embodiments, the application management platform 110 may determine an intent of the user input and obtain corresponding target data based on the intent. For example, if the user input is the text "what month the highest sales of commodity a occurred in the past year? The application management platform 110 may determine that the user input is intended to analyze sales data of the commodity a for the past year, and may further obtain sales data of the commodity a for the past year from the data table. Based on sales data for the past year, sales per month for the past year can be calculated. In this example, sales per month and sales data of the past year may be used as target data.
In some embodiments, deriving the target data from the user input may be implemented using a model. For example, the model may generate data query instructions based on user input to query sales for each month of the past year.
At block 220, the application management platform 110 generates at least one processing instruction for the target data using the target model based on the source information regarding the source of the target data. The processing instructions may be used to perform any type of data processing on the target data, such as, but not limited to, data conversion, data cleansing, ordering, various numerical operations, and the like.
The source information may include, for example, one or more data query instructions for retrieving target data. The data query instruction herein may be, for example, structured Query Language (SQL), which may inform the target model how the target data is queried, and may help the target model to better understand the data. The source information may also include, for example, meta information of one or more data objects from which the target data originates, e.g., structure information of a data table. The meta information of the data object may for example comprise fields comprised by the data object. The source information may also include, for example, examples of data records in one or more data objects. Taking the data object as an example of a data table, an example of a data record may include, for example, the first few rows of the data table.
The target model may be a model deployed locally on the application management platform 110 or may be a model deployed at other electronic devices. The target model may be based on any suitable model structure, including, but not limited to, a transducer model, a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Deep Neural Network (DNN), and the like. In some embodiments, the target model may be a Language Model (LM).
In some embodiments, the application management platform 110 may obtain address information for the target data. The address information may indicate a storage location of the target data. In some embodiments, the application management platform 110 may store the target data to the instruction execution environment prior to generating the at least one processing instruction. In this case, the address information acquired by the application management platform 110 may indicate a storage location of the target data in the instruction execution environment. By way of example, the instruction execution environment may be a limited execution environment that allows a user to execute data processing instructions, such as code in a predetermined language, within an isolated secure space. Such an instruction execution environment provides a secure, isolated, and controllable environment. Sandboxes are one example of an instruction execution environment.
The application management platform 110 may generate a prompt word input (prompt) for the target model, which may also be referred to as prompt information, based on, for example, address information, source information, and user input. The application management platform 110 may, for example, obtain a hint word template for the target model and determine hint information for the target model by populating the hint word template with address information, source information, and user input. In some embodiments, the application management platform 110 may generate only one hint information and obtain the at least one processing instruction by providing the hint information to the object model.
For example, the application management platform 110 may generate first hint information for the object model based on address information, source information, and user input. The application management platform 110 may provide the first hint information to the target model. After the target model receives the first prompt information, a corresponding model output can be generated based on the first prompt information. The model output may, for example, indicate a first processing instruction of the at least one processing instruction. The application management platform 110 may obtain a model output from the target model and determine a first of the at least one processing instruction based on the model output.
Therefore, the prompt information can be generated based on the address information and the source information of the data, and the prompt information can be provided for the target model, so that the data volume processed by the target model can be reduced, and the accuracy of information processing is improved. Furthermore, by providing the address of the target data to the model instead of providing all the target data to the model, it is possible to avoid the input to the model exceeding the input capacity as much as possible.
In some embodiments, the application management platform 110 may also generate at least one hint information and obtain at least one processing instruction by providing the at least one hint information to the object model, each processing instruction corresponding to one hint information. In particular, the application management platform 110 may, for example, utilize a goal model to determine at least one task indicated by the user input. If the at least one task includes a plurality of tasks, the application management platform 110 may determine corresponding prompt information for each task. The application management platform 110 may further determine a processing instruction corresponding to each task based on the prompt information corresponding to each task.
At block 230, the application management platform 110 obtains at least one processing result by executing at least one processing instruction on the target data, respectively. In some embodiments, if the target data is stored in the instruction execution environment, at least one processing instruction generated by the application management platform 110 is executed in the preset instruction execution environment. The application management platform 110 may, for example, send at least one processing instruction to a preset instruction execution environment in order to execute the at least one processing instruction in the instruction execution environment. The application management platform 110 may obtain at least one processing result of at least one processing instruction from the instruction execution environment.
If at least one processing instruction includes a plurality of processing instructions, the plurality of processing instructions may not affect each other or may affect each other. For example, the application management platform 110 may determine one processing instruction based on the processing result of the other processing instruction. The application management platform 110 may determine, for example, using the goal model, that the user input is indicative of at least a first task and a second task. For example, if the user input includes the text "what month the highest sales of commodity a occurred in the past year? What is the average sales per month? The application management platform 110 may determine that the user input indicates that task a "determine the month at which the highest sales for commodity a occurred over the past year" and task B "determine the month average sales for commodity a over the past year using the goal model.
The application management platform 110 may generate first hint information associated with the first task based on the address information, the source information, and the user input. The application management platform 110 may provide the first hint information to the object model to obtain a first processing instruction of the at least one processing instruction. The first processing instruction is for a first task. The application management platform 110 may obtain a first processing result of the first processing instruction. For example, the first processing instruction may be an instruction for maximizing the sales amount of 12 sales, and the first processing result is the maximum value and the month corresponding to the maximum value.
The application management platform 110 may generate second hint information associated with the second task based on the address information, the source information, and the first processing result. The application management platform 110 may provide the second hint information to the object model to obtain a second processing instruction of the at least one processing instruction. The second processing instruction is for a second task. For example, the second processing instruction may be an instruction to calculate an average value of 12 sales, and the second processing result is the average value.
In some embodiments, the application management platform 110 may also complete execution in response to a given processing instruction of the at least one processing instruction, update the target data based on a processing result of the given processing instruction, and the generation of the processing instructions subsequent to the given processing instruction is based on the updated target data. Illustratively, if the processing result of processing instruction A indicates that new data is generated, the new data will be added to the target data. Processing instructions subsequent to processing instruction a will be generated based on the target data to which the new data is added. If the processing result of processing instruction B indicates that the target data is purged, the application management platform 110 will remove the purged data from the target data. The processing instructions following processing instruction B will be generated based on the target data that removes the flushed data.
At block 240, the application management platform 110 generates an analysis result for the target data as a response to the user input using the target model based on the at least one processing result. The analysis results may include, for example, various insight analyses related to user input. Continuing with the example above, the analysis results may include, for example, a summary of the change in sales of commodity A over the past year.
In some embodiments, the analysis results may include, for example, reference information indicating the source of one or more items of data in the analysis results. In such an embodiment, the source of the data on which the model is dependent may be indicated in a prompt provided to the model, thereby facilitating enhanced confidence in the insight, thereby providing the user with a trusted analysis result.
The application management platform 110 may, for example, receive user input via an interactive window (e.g., interactive window 142) and provide analysis results via the interactive window. The analysis results may be provided to the user, for example, in the form of a session message from the digital assistant.
The application management platform 110 may, for example, provide at least one processing result to the target model to generate an analysis result for the target data using the target model. In some embodiments, the application management platform 110 may generate a hint word input for the target model based on at least one processing result and provide the generated hint word input to the target model. The application management platform 110 may, for example, generate a hint word input based on the at least one processing result that may instruct the object model to analyze the at least one processing result. The application management platform 110 may also generate at least one alert word input, for example, based on at least one of the processing results, each alert word input indicating an analysis of the corresponding processing result.
In some embodiments, the application management platform 110 may also determine the input consumption of the source information and the at least one processing result and the input capacity of the target model. The input consumption amount may represent an amount of data to be input from the source information and the at least one processing result as the target model. One example of the input consumption may be the number of tokens (token) consumed by the input to the model, and accordingly, the input capacity may be the total number of tokens that can be provided to the model in one input. The application management platform 110 may compare the input consumption amount with the input capacity of the target model to determine whether the input consumption amount exceeds the input capacity of the target model. If the input consumption does not exceed the input capacity, the application management platform 110 may directly process at least one processing result using the target model to determine an analysis result for the target data. If the input consumption exceeds the input capacity, the application management platform 110 may generate a third hint information based on the at least one processing result to instruct the object model to summarize the at least one processing result. The application management platform 110 may provide the third hint information to the object model to obtain the analysis result.
For example, taking an input capacity of 50 (e.g., the unit is the number of tokens) as an example, if the input consumption is 40, the application management platform 110 may determine that the input consumption does not exceed the input capacity, and further directly process at least one processing result using the target model to determine an analysis result for the target data. If the input consumption is 60, the application management platform 110 may determine that the input consumption exceeds the input capacity, and may generate third hint information based on the at least one processing result to instruct the object model to summarize the at least one processing result. The application management platform 110 may provide the third hint information to the object model to obtain the analysis result.
Thus, when the input consumption reaches the upper limit (i.e., the input capacity is reached), the application management platform 110 may prompt the target model to summarize according to the currently existing results, may provide at least a portion of the analysis results to the user, and may improve the user experience of the user.
Referring to fig. 3, fig. 3 illustrates a schematic diagram of an example 300 of information processing according to some embodiments of the present disclosure. As shown in fig. 3, the application management platform 110 may obtain the target data 304 indicated by the user input 340 in response to obtaining the user input 340. Continuing with the example above, if the user input 340 is "summarize sales of commodity A for the past year," then the target data 304 may be sales data for commodity A for the past year. The application management platform 110 may utilize a target model (e.g., model 330) to generate at least one processing instruction for the target data 304 based on the source information 306 regarding the source of the target data 301. The processing instructions may be used to perform any type of data processing on the target data, such as, but not limited to, data conversion, data cleansing, ordering, various numerical operations, and the like. Continuing with the example above, if the user input 340 is "summarize sales of good A for the past year," the processing instructions may be used to calculate sales and/or sales of good A for each month over the past 12 months, etc.
As previously described at block 220, the application management platform 110 may generate hints information for the model 330 based at least on the source information 306 and provide the hints information to the model 330. Model 330 may output at least one processing instruction for target data 304. Model 330 may be a model local to application management platform 110 or may be a model deployed at a remote device. If the model 330 is deployed locally on the application management platform 110, the application management platform 110 may directly utilize the model 330 to determine the at least one processing instruction. If the model 330 is deployed at a remote device, the application management platform 110 may invoke the model 330 deployed at the remote device to determine at least one processing instruction via a communication connection with the remote device.
The source information 306 may include one or more data query instructions for retrieving target data, meta information 302 of one or more data objects from which the target data originated, and/or data record examples 303 in the one or more data objects. For example, the source information 306 may include one or more query instructions for obtaining sales data for the good a over the past year. The application management platform 110 may, for example, forward the target data 304 to the instruction execution environment 320 prior to generating the at least one processing instruction to store the target data 304 to the instruction execution environment 320. The application management platform 110 may obtain address information for the target data 304, the address information indicating a storage location of the target data 304 in the instruction execution environment 320. The application management platform 110 may generate hint information 310 (e.g., first hint information) for the object model based on the address information, the source information 306, and the user input 340.
Regarding the particular manner in which the at least one processing instruction is generated, the application management platform 110 may, for example, perform the various steps included in block 350 to generate the at least one processing instruction. Specifically, at block 351, the application management platform 110 may determine a plurality of tasks indicated by the user input 340. For example, the application management platform 110 may provide hints generated based on the user input 340 to the target model from which the tasks are parsed. At block 352, the application management platform 110 may generate a plurality of hints information based on the plurality of tasks. At block 353, the application management platform 110 may provide a plurality of hints information to the goal model to determine a plurality of processing instructions corresponding to the plurality of tasks using the goal model. It should be noted that at least one of the plurality of steps included in block 350 may be determined by application management platform 110 via model 330. The application management platform 110 may perform this at least one step directly with the model 330 or by invoking the model 330 from a remote device. As an example, at block 351, the application management platform 110 may provide the hint information generated based on the user input 340 to the target model, which parses out the tasks. At block 352, the application management platform 110 may generate corresponding hints information for the tasks, respectively. At block 353, the generated hint information may be provided to the target model to generate processing instructions corresponding to the task from the target model.
Further, at block 360, the application management platform 110 may obtain at least one processing result by executing at least one processing instruction on the target data 304, respectively. For example, the processing result may be the calculated sales and/or sales of the commodity a for each month in the past year. In some embodiments, if multiple processing instructions are included, the application management platform 110 may execute the processing instructions on the target data 304 multiple times to obtain multiple processing results. The application management platform 110 may, for example, provide at least one processing instruction to the instruction execution environment 320 and obtain at least one processing result corresponding to the at least one processing instruction from the instruction execution environment 320.
At block 370, the application management platform 110 may provide at least one processing result to the target model (and likewise, may be the model 330, for example) to generate an analysis result for the target data 304 as a response to the user input 340 using the target model. Continuing with the example above, sales and/or sales for item A per month may be provided to the target model. In this way, the objective model may output analysis results of sales and/or sales, such as a trend of change in sales and/or sales, a month in which the highest sales and/or sales occur, a month in which the lowest sales and/or sales occur, and the like. In some embodiments, the application management platform 110 may determine whether the source information 306 and the input consumption 301 of the at least one processing result exceeds the input capacity 305 of the target model. The application management platform 110 may generate, based on the at least one processing result, hint information that instructs the goal model to summarize the at least one processing result in response to determining that the input consumption 301 exceeds the input capacity 305. The application management platform 110 may provide the hint information to the target model to obtain the analysis result. The application management platform 110 may directly provide at least one processing result to the target model to obtain an analysis result in response to determining that the input consumption 301 does not exceed the input capacity 305.
In summary, according to embodiments of the present disclosure, processing instructions for data may be generated by means of a model, and analysis results of the data may be determined based on the processing results of the data instructions by means of the model. This helps to improve the efficiency and accuracy of information processing. In addition, the processing capacity of the model on complex information and large data volume information is enhanced.
Embodiments of the present disclosure also provide corresponding apparatus for implementing the above-described methods or processes. Fig. 4 illustrates a schematic block diagram of an apparatus 400 for information processing according to some embodiments of the present disclosure. The apparatus 400 may be implemented in or included in the application management platform 110, for example. The various modules/components in apparatus 400 may be implemented in hardware, software, firmware, or any combination thereof.
As shown, the apparatus 400 includes a target data acquisition module 410 configured to acquire target data indicated by user input in response to receiving the user input. The apparatus 400 further comprises a processing instruction generation module 420 configured to generate at least one processing instruction for the target data using the target model based on source information related to the source of the target data. The apparatus 400 further comprises a processing result acquisition module 430 configured to acquire at least one processing result by executing at least one processing instruction on the target data, respectively. The apparatus 400 further comprises an analysis result generation module 440 configured to generate an analysis result for the target data as a response to the user input using the target model based on the at least one processing result.
In some embodiments, the processing instruction generation module 420 includes: an address information acquisition module configured to acquire address information for target data, the address information indicating a storage location of the target data; the first prompt information generation module is configured to generate first prompt information aiming at the target model based on the address information, the source information and the user input; and a first processing instruction acquisition module configured to provide the first hint information to the target model to obtain a first processing instruction of the at least one processing instruction.
In some embodiments, the at least one processing instruction is executed in a preset instruction execution environment, and the apparatus 400 further comprises: and a target data storage module configured to store target data to the instruction execution environment prior to generating the at least one processing instruction, the address information indicating a storage location of the target data in the instruction execution environment.
In some embodiments, the apparatus 400 further comprises: a task determination module configured to determine, using the target model, that the user input is indicative of at least a first task and a second task, and wherein the first processing instructions are associated with the first task, and the processing instruction generation module 420 further comprises: the second prompt information generation module is configured to generate second prompt information aiming at the target model based on the address information, the source information and the first processing result of the first processing instruction; and a second processing instruction acquisition module configured to provide second hint information to the target model to obtain a second processing instruction of the at least one processing instruction for the second task.
In some embodiments, the source information includes at least one of: one or more data query instructions for retrieving target data, meta information of one or more data objects from which the target data originates, or data record instances in the one or more data objects.
In some embodiments, the analysis result generation module 440 includes: a capacity determination module configured to determine whether an input consumption amount of the source information and the at least one processing result exceeds an input capacity of the target model, the input consumption amount representing an input data amount having the source information and the at least one processing result as the target model; a third hint information generating module configured to generate third hint information based on the at least one processing result to instruct the target model to summarize the at least one processing result in response to determining that the input consumption exceeds the input capacity; and the analysis result acquisition module is configured to provide the third prompt information for the target model so as to obtain an analysis result.
In some embodiments, the apparatus 400 further comprises: the target data updating module is configured to update the target data based on a processing result of a given processing instruction in response to completion of execution of the given processing instruction of the at least one processing instruction, and generation of the processing instruction subsequent to the given processing instruction is based on the updated target data.
In some embodiments, the analysis results include reference information indicating a source of one or more items of data in the analysis results.
The elements and/or modules included in apparatus 400 may be implemented in various manners, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and/or modules may be implemented using software and/or firmware, such as machine executable instructions stored on a storage medium. In addition to or in lieu of machine-executable instructions, some or all of the units and/or modules in apparatus 400 may be implemented at least in part by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include Field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standards (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.
Fig. 5 illustrates a block diagram of an electronic device 500 in which one or more embodiments of the disclosure may be implemented. It should be understood that the electronic device 500 shown in fig. 5 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 500 illustrated in fig. 5 may include or be implemented as the application management platform 110 of fig. 1, or the apparatus 400 of fig. 4.
As shown in fig. 5, the electronic device 500 is in the form of a general-purpose electronic device. The components of electronic device 500 may include, but are not limited to, one or more processors or processing units 510, memory 520, storage 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 a real or virtual processor and is capable of performing various processes according to programs stored in the memory 520. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capabilities of electronic device 500.
Electronic device 500 typically includes multiple computer storage media. Such a medium may be any available media that is accessible by electronic device 500, including, but not limited to, volatile and non-volatile media, removable and non-removable media. The memory 520 may be volatile memory (e.g., registers, cache, random Access Memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 may be a removable or non-removable media and may include machine-readable media such as flash drives, magnetic disks, or any other media that may be capable of storing information and/or data and that may be accessed within electronic device 500.
The electronic device 500 may further include additional removable/non-removable, volatile/nonvolatile storage media. Although not shown in fig. 5, a magnetic disk drive for reading from or writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data medium interfaces. Memory 520 may include a computer program product 525 having one or more program modules configured to perform the various methods or acts of the various embodiments of the present disclosure.
The communication unit 540 enables communication with other electronic devices through a communication medium. Additionally, the functionality of the components of electronic device 500 may be implemented in a single computing cluster or in multiple computing machines capable of communicating over a communication connection. Thus, the electronic device 500 may operate in a networked environment using logical connections to one or more other servers, a network Personal Computer (PC), or another network node.
The input device 550 may be one or more input devices such as a mouse, keyboard, trackball, etc. The output device 560 may be one or more output devices such as a display, speakers, printer, etc. The electronic device 500 may also communicate with one or more external devices (not shown), such as storage devices, display devices, etc., with one or more devices that enable a user to interact with the electronic device 500, or with any device (e.g., network card, modem, etc.) that enables the electronic device 500 to communicate with one or more other electronic devices, as desired, via the communication unit 540. Such communication may be performed via an input/output (I/O) interface (not shown).
According to an exemplary implementation of the present disclosure, a computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method described above is provided. According to an exemplary implementation of the present disclosure, there is also provided a computer program product tangibly stored on a non-transitory computer-readable medium and comprising computer-executable instructions that are executed by a processor to implement the method described above.
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus, devices, and computer program products implemented according to the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer readable program instructions may be provided to a processing unit of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various implementations of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description of implementations of the present disclosure has been provided for illustrative purposes, is not exhaustive, and is not limited to the implementations disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various implementations described. The terminology used herein was chosen in order to best explain the principles of each implementation, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand each implementation disclosed herein.
Claims (11)
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410851923.1A CN118839768A (en) | 2024-06-27 | 2024-06-27 | Information processing method, apparatus, device and storage medium |
| PCT/CN2025/080095 WO2026001060A1 (en) | 2024-06-27 | 2025-02-28 | Information processing method and apparatus, device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410851923.1A CN118839768A (en) | 2024-06-27 | 2024-06-27 | Information processing method, apparatus, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118839768A true CN118839768A (en) | 2024-10-25 |
Family
ID=93141635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410851923.1A Pending CN118839768A (en) | 2024-06-27 | 2024-06-27 | Information processing method, apparatus, device and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN118839768A (en) |
| WO (1) | WO2026001060A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2026001060A1 (en) * | 2024-06-27 | 2026-01-02 | 北京字跳网络技术有限公司 | Information processing method and apparatus, device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114205417A (en) * | 2021-11-16 | 2022-03-18 | 上海翀远智能科技有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN116821103A (en) * | 2023-08-29 | 2023-09-29 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and computer readable storage medium |
| CN117235223A (en) * | 2023-09-18 | 2023-12-15 | 北京百度网讯科技有限公司 | HVAC system data processing method, device and equipment based on large language model |
| CN117235222A (en) * | 2023-09-18 | 2023-12-15 | 北京奇艺世纪科技有限公司 | Model-based interaction method, device, electronic device and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11741308B2 (en) * | 2020-05-14 | 2023-08-29 | Oracle International Corporation | Method and system for constructing data queries from conversational input |
| CN115905284B (en) * | 2022-11-15 | 2025-07-22 | 北京火山引擎科技有限公司 | Data processing method, device, equipment and storage medium |
| CN117273017A (en) * | 2023-09-21 | 2023-12-22 | 广州趣研网络科技有限公司 | Information processing method, information processing device, computer equipment and storage medium |
| CN117555897A (en) * | 2023-10-10 | 2024-02-13 | 北京百度网讯科技有限公司 | Data query methods, devices, equipment and storage media based on large models |
| CN117952212A (en) * | 2024-01-02 | 2024-04-30 | 科大讯飞股份有限公司 | Data processing method and device based on large language model and blockchain |
| CN118069820B (en) * | 2024-04-22 | 2024-08-02 | 来未来科技(浙江)有限公司 | Conversational data analysis method, device, equipment and storage medium |
| CN118839768A (en) * | 2024-06-27 | 2024-10-25 | 北京字跳网络技术有限公司 | Information processing method, apparatus, device and storage medium |
-
2024
- 2024-06-27 CN CN202410851923.1A patent/CN118839768A/en active Pending
-
2025
- 2025-02-28 WO PCT/CN2025/080095 patent/WO2026001060A1/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114205417A (en) * | 2021-11-16 | 2022-03-18 | 上海翀远智能科技有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN116821103A (en) * | 2023-08-29 | 2023-09-29 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and computer readable storage medium |
| CN117235223A (en) * | 2023-09-18 | 2023-12-15 | 北京百度网讯科技有限公司 | HVAC system data processing method, device and equipment based on large language model |
| CN117235222A (en) * | 2023-09-18 | 2023-12-15 | 北京奇艺世纪科技有限公司 | Model-based interaction method, device, electronic device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 蒋宁等: "金融大模型揭示数字金融领域大模型的应用与发展趋势精装典藏版", 31 March 2024, 中国科学技术出版社, pages: 32 - 35 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2026001060A1 (en) * | 2024-06-27 | 2026-01-02 | 北京字跳网络技术有限公司 | Information processing method and apparatus, device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2026001060A1 (en) | 2026-01-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2025157280A1 (en) | Interaction method and apparatus, device and storage medium | |
| CN119003039A (en) | Method, apparatus, device and storage medium for information processing | |
| CN119002767A (en) | Information processing method, apparatus, device and storage medium | |
| CN118839768A (en) | Information processing method, apparatus, device and storage medium | |
| CN119003558B (en) | Information processing method, apparatus, device and storage medium | |
| CN119002749B (en) | Information processing methods, apparatus, equipment and storage media | |
| CN119004403A (en) | Information processing method, apparatus, device and storage medium | |
| CN118838519A (en) | Information processing method, apparatus, device and storage medium | |
| CN119003324A (en) | Method, device, equipment and storage medium for generating test cases | |
| CN113687881A (en) | Metadata calling method and device, electronic equipment and storage medium | |
| CN120744094B (en) | Data processing methods, apparatus, equipment, and storage media used in project management | |
| CN119135667B (en) | Method, apparatus, device and storage medium for function calling | |
| CN119312393A (en) | Data processing method, device, equipment, storage medium and program product | |
| CN119003515B (en) | Data processing method, device, equipment and storage medium | |
| CN119292707A (en) | Information processing method, device, equipment, storage medium and program product | |
| CN119311734A (en) | Method, apparatus, device, medium and program product for data query | |
| CN120848870A (en) | Model-based application building method, device, equipment, medium and program product | |
| CN119631091A (en) | Method, device, equipment and storage medium for dialogue interaction | |
| CN119917604A (en) | Method, device, apparatus and medium for storing data | |
| CN119088435A (en) | Information processing method, device, equipment, storage medium and program product | |
| CN120632025A (en) | Method, device, equipment, medium and program product for generating prompt words for large models | |
| WO2025245749A1 (en) | Content pushing method and apparatus, device, and storage medium | |
| CN120687185A (en) | Interface interaction method, device, equipment and storage medium | |
| CN119088438A (en) | Information processing and application configuration method, device, equipment, storage medium and product | |
| WO2025200591A1 (en) | Method and apparatus for creating digital assistant, and device and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |