Data processing method and electronic equipment

Abstract

The invention discloses a data processing method, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining target input; if the target input meets a first condition, obtaining first information; outputting second information based on the first information, wherein the second information is used for prompting to obtain first time of target output; the target output is generated by a target model based on the target input, and the first time is related to the first information.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a data processing method and electronic device. Background Art

[0002] With the development of artificial intelligence technology, the application of model-based data processing systems is becoming more and more widespread. However, the current data processing system only outputs reply information in a single way after receiving the user's input information, and its intelligence is relatively poor. Summary of the invention

[0003] The purpose of this application is to provide a data processing method, device, equipment, storage medium and program product, including the following technical solutions:

[0004] The first aspect of the present application provides a data processing method, the method comprising:

[0005] Get target input;

[0006] If the target input satisfies a first condition, obtaining first information;

[0007] Second information is output based on the first information, where the second information is used to prompt a first time for obtaining a target output; the target output is generated by a target model based on the target input, and the first time is related to the first information.

[0008] In a possible implementation, obtaining the first information and outputting the second information based on the first information includes any of the following:

[0009] Obtaining first sub-information, determining the first time based on the first sub-information, and outputting the second information; the first sub-information represents the processing performance of the electronic device running the target model;

[0010] obtaining second sub-information, determining the first time based on the second sub-information, and outputting the second information; the second sub-information represents the occupation of available processing resources of the electronic device by the non-target model;

[0011] Obtaining third sub-information, determining the first time based on the third sub-information, and outputting the second information; the third sub-information represents the degree of understanding of the field to which the target input belongs by the input object;

[0012] The first information includes first sub-information, second sub-information and / or third sub-information.

[0013] In a possible implementation, obtaining the first information and outputting the second information based on the first information includes:

[0014] Obtaining fourth sub-information, where the fourth sub-information is related to the input object and / or the input environment;

[0015] determining a second time based on the fourth sub-information, the second time representing a time that the input object can wait;

[0016] The second information is output based on the first time and the second time; the second information is also used to prompt the input object to trigger the target model to run or perform other tasks.

[0017] In a possible implementation, if the first information includes the third sub-information, the method includes:

[0018] Determining, based on the third sub-information, the degree of understanding of the field to which the target input belongs by the input object;

[0019] If the input object's understanding of the field to which the target input belongs meets a second condition, third information is output based on the first time, and the third information is used to prompt the selection of a knowledge base.

[0020] A second aspect of the present application provides a data processing method, the method comprising:

[0021] Get target input;

[0022] If the target input satisfies a first condition, obtaining first information; the first information is related to the input object;

[0023] Fourth information is output based on the first information; the fourth information includes a first output or a second output, the first output or the second output is generated by a target model based on the target input, and the first output is different from the second output.

[0024] In a possible implementation, outputting fourth information based on the first information includes any one of the following:

[0025] If the first information indicates that the input object is a first input object, the output includes fourth information of the first output; if the first information indicates that the input object is a second input object, the output includes fourth information of the second output; the first input object is different from the second input object;

[0026] If the first information represents that the input object is the first input object and is in the first scene, the output includes the fourth information of the first output; if the first information represents that the input object is the first input object and is in the second scene, the output includes the fourth information of the second output; the first scene is different from the second scene.

[0027] In a possible implementation, outputting fourth information based on the first information includes any one of the following:

[0028] If the first information represents that the time during which the input object can wait satisfies the second condition, outputting fourth information including the first output;

[0029] If the first information represents that the degree of understanding of the input object about the field to which the target input belongs satisfies a third condition, outputting fourth information including the first output;

[0030] The quality of the first output is higher than the quality of the second output.

[0031] In a possible implementation, when outputting fourth information based on the first information, the method further includes:

[0032] outputting fifth information and / or sixth information;

[0033] The fifth information includes at least one source data and an associated display relationship between the source data and the output included in the fourth information;

[0034] The sixth information includes source data with an identifier, wherein the identifier indicates that the input object is associated with the source data.

[0035] A third aspect of the present application provides a data processing method, the method comprising:

[0036] Get target input;

[0037] If the target input satisfies a first condition, obtaining first information;

[0038] determining a target strategy based on the first information;

[0039] The target strategy represents a strategy for generating a target output, including any of the following:

[0040] Selecting a model matching the first information from among a plurality of models as a target model according to the first information, and generating a target output based on the target model;

[0041] Determining the number of calls to the target model according to the first information;

[0042] Determine, according to the first information, a step of generating the target output by the target model based on the target input and the target information;

[0043] Determining, according to the first information, a depth of information search in a preset information source or a selected knowledge base based on the target input;

[0044] The extent of information search in the preset information source or the selected knowledge base based on the target input is determined according to the first information.

[0045] The fourth aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the data processing method of the first aspect or any implementation method of the first aspect.

[0046] A fifth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0047] The memory is used to store computer programs;

[0048] The processor is used to execute the computer program so that the electronic device can implement the data processing method of any aspect of the first to third aspects or any implementation manner of any aspect.

[0049] In a fifth aspect, the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the data processing method of any aspect of the first to third aspects or any implementation of any of the aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] 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. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0051] Figure 1 A flowchart of an implementation of the data processing method provided in this application;

[0052] Figure 2a A flowchart for obtaining first information and outputting second information based on the first information provided in the present application;

[0053] Figure 2b An example diagram of an interaction provided by the present application, in which first information is obtained after a target input is obtained, and second information is output based on the first information;

[0054] Figure 3a Another implementation flowchart of obtaining first information and outputting second information based on the first information provided by the present application;

[0055] Figure 3b Another example diagram of interaction provided by the present application, in which first information is obtained after target input is obtained, and second information is output based on the first information;

[0056] Figure 4aAnother implementation flowchart of obtaining first information and outputting second information based on the first information provided by the present application;

[0057] Figure 4b Another example diagram of interaction provided by the present application, in which first information is obtained after target input is obtained, and second information is output based on the first information;

[0058] Figure 5a Another implementation flowchart of obtaining first information and outputting second information based on the first information provided by the present application;

[0059] Figure 5b Another example diagram of interaction provided by the present application, in which first information is obtained after target input is obtained, and second information is output based on the first information;

[0060] Figure 6 An example diagram of an interaction provided by the present application, in which first information is obtained after a target input is obtained, and third information is output based on the first information;

[0061] Figure 7a Another implementation flow chart of the data processing method provided in this application;

[0062] Figure 7b An example diagram of an interaction provided by the present application, in which after obtaining a target input inputted by a first input object A, first information is obtained, and fourth information is outputted based on the first information;

[0063] Figure 7c Another example diagram of interaction provided by the present application, in which after obtaining a target input inputted by a second input object B, first information is obtained, and fourth information is outputted based on the first information;

[0064] Figure 7d Another example diagram of interaction provided by the present application, in which after obtaining a target input inputted by a first input object A, first information is obtained, and fourth information is outputted based on the first information;

[0065] Figure 7e Another example diagram of interaction provided by the present application, in which after obtaining a target input inputted by a first input object A, first information is obtained, and fourth information is outputted based on the first information;

[0066] Figure 7f Another example diagram of an interaction provided by the present application, in which after obtaining a target input of an input object, first information is obtained, and fourth information is output based on the first information;

[0067] Figure 7g Another example diagram of an interaction provided by the present application, in which after obtaining a target input of an input object, first information is obtained, and fourth information is output based on the first information;

[0068] Figure 7h An example diagram of outputting sixth information provided by the present application;

[0069] Figure 8 A flowchart of another implementation of the data processing method provided in this application;

[0070] Fig. 9 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0071] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0072] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0073] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0074] The data processing method provided in the embodiment of the present application can be used in an electronic device, which is deployed with a machine learning model, such as a neural network model, which can include but is not limited to any of the following: Convolutional Neural Network (CNN), Deep Convolutional Network (DCN), Recurrent Neural Network (RNN), Large Model, etc. Large Models can include but are not limited to any of the following: Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), etc.

[0075] An implementation flow chart of the data processing method provided in the embodiment of the present application is as follows Figure 1 As shown, this may include:

[0076] Step S101: Obtain target input.

[0077] The target input is the interactive content input by the input object (eg, user), which may include but is not limited to content in at least one of the following formats: text, file, image, etc.

[0078] Step S102: If the target input satisfies the first condition, first information is obtained.

[0079] The first condition is used to determine whether it is necessary to output the second information to prompt the input object to obtain the target output based on the target input.

[0080] Optionally, the target input satisfying the first condition may include: the target input being a complex question.

[0081] As an example, the complexity of the target input may be determined. If the complexity is greater than the target complexity, it is determined that the target input belongs to a complex problem. Otherwise, it is determined that the target input does not belong to a complex problem. The complexity of the target input may be determined in any of the following ways:

[0082] Semantic analysis is performed on the target input to determine the number of semantics contained in the target input (i.e., the number of different semantic information contained in the target input). The complexity of the target input is positively correlated with the number of semantics contained in the target input, i.e., the more semantics the target input contains, the higher the complexity of the target input.

[0083] Semantic analysis is performed on the target input to determine the correlation between the various semantic information contained in the target input. The complexity of the target input is positively correlated with the correlation between the various semantic information contained in the target input, that is, the greater the correlation between the various semantic information contained in the target input, the higher the complexity of the target input.

[0084] As an example, the target input may be processed by a pre-trained classification model to obtain a classification result corresponding to the target input, and the classification result indicates whether the target input belongs to a complex problem.

[0085] The first information may include: information related to at least one of an input object, an input environment, and an electronic device.

[0086] Step S103: output second information based on the first information, the second information is used to prompt the first time to obtain the target output; the target output is generated by the target model based on the target input, and the first time is related to the first information.

[0087] Before the target model generates the target output based on the target input, the present application estimates the time to obtain the target output based on the first information, and then outputs the second information so that the input object can know the feedback time of the target output (ie, the first time).

[0088] The data processing method provided in the embodiment of the present application, after obtaining the target input, if the target input satisfies the first condition, will output second information based on the first information to inform the input object how long it will take to obtain the target output, and then the target model will generate and output the target output based on the target input. The output mode is changed, so that the input object can clearly understand the specific situation of the interactive system obtaining the target output based on the target input, the interaction mode with the input object is increased, the intelligence of the data processing system based on the large model is improved, and the input object's demand for intelligent interaction is met.

[0089] In an optional embodiment, a flowchart of obtaining the first information and outputting the second information based on the first information is as follows: Figure 2a As shown, this may include:

[0090] Step S201: Obtain first sub-information.

[0091] The first sub-information is included in the first information, that is, the first information includes the first sub-information. The first sub-information characterizes the processing performance of the electronic device running the target model. The first sub-information may include, but is not limited to, at least part of the following information: the number of cores, main frequency and cache size of the processor, memory capacity and frequency, hard disk type and storage capacity, video memory size, number of stream processors, bus width, performance of installed software, etc.

[0092] Among them, the processing performance of electronic devices is positively correlated with the number of cores of the processor, that is, the more cores the processor has, the higher the processing performance of the electronic device;

[0093] The processing performance of electronic devices is positively correlated with the main frequency of the processor, that is, the greater the main frequency of the processor, the faster the computing speed of the electronic device and the higher the processing performance;

[0094] The processing performance of an electronic device is positively correlated with the cache size of the processor, that is, the larger the cache of the processor, the faster the data processing speed of the processor, and the higher the processing performance of the electronic device;

[0095] The processing performance of an electronic device is positively correlated with the memory capacity of the electronic device, that is, the larger the memory capacity of the electronic device, the higher the processing performance;

[0096] The processing performance of an electronic device is positively correlated with the memory frequency of the electronic device, that is, the higher the memory frequency of the electronic device, the faster the data transmission of the memory, and the higher the processing performance of the electronic device;

[0097] Different types of hard disks have different read and write speeds, and electronic devices have different processing performances; the processing performance of electronic devices is positively correlated with the read and write speeds of the hard disk, that is, the higher the read and write speed of the hard disk, the higher the processing performance of the electronic device;

[0098] The processing performance of electronic devices is positively correlated with the storage capacity of the hard disk, that is, the larger the storage capacity of the hard disk, the higher the processing performance of the electronic device;

[0099] The processing performance of electronic devices is positively correlated with the size of video memory, that is, the larger the video memory, the stronger the graphics card's ability to process images and videos, and the higher the processing performance of electronic devices;

[0100] The stream processor is the core processing unit in the graphics card. The processing performance of the electronic device is positively correlated with the number of stream processors in the graphics card. That is, the more stream processors there are, the better the processing performance of the graphics card and the higher the processing performance of the electronic device.

[0101] The wider the bus width, the faster the data transfer and the higher the processing performance of the electronic equipment.

[0102] The higher the performance of the software called by the electronic device, the higher the processing performance of the electronic device.

[0103] Step S202: Determine a first time (ie, the time taken for the target model to generate a target output based on a target input) based on the first sub-information.

[0104] Optionally, the first sub-information represents that the higher the processing performance of the electronic device is, the shorter the first time taken by the target model to generate the target output based on the target input is; conversely, the first sub-information represents that the lower the processing performance of the electronic device is, the longer the first time taken by the target model to generate the target output based on the target input is.

[0105] Step S203: outputting the second information. The second information carries the first time determined based on the first sub-information.

[0106] like Figure 2b As shown, it is an interactive example diagram provided by an embodiment of the present application, in which after obtaining a target input, first information is obtained, and second information is output based on the first information. In this example, the target input is "Help me sort out some mainstream opinions recently published by famous experts in the top 3 companies in the field of patent writing", and the second information is "OK, this question is more complicated. According to the performance of the machine, it will take me about 3 minutes to reply to you".

[0107] In an optional embodiment, another implementation flowchart of obtaining the first information and outputting the second information based on the first information is as follows: Figure 3a As shown, this may include:

[0108] Step S301: Obtain second sub-information.

[0109] The second sub-information is included in the first information, that is, the first information includes the second sub-information. The second sub-information represents the occupation of the available processing resources of the electronic device by the non-target model.

[0110] The processing resources of the electronic device may include but are not limited to: a processor, memory, etc.

[0111] The available processing resources of the electronic device refer to the available processing resources of the electronic device when the electronic device obtains the target input.

[0112] The non-target model may include: other applications to be run in the electronic device except the target model. The non-target model may be determined based on the schedule information of the input object. For example, if the user schedule information indicates that the user has a meeting at 15:00-16:00, the non-target model may include conference software.

[0113] The occupation of available processing resources by non-target models may include but is not limited to: the start time when the available processing resources are occupied by the non-target model, the duration of the occupation of the available processing resources by the non-target model, the proportion of the available processing resources occupied by the non-target model, the priority of the non-target model, etc.

[0114] Step S302: Determine the first time (ie, the time taken for the target model to generate the target output based on the target input) based on the second sub-information.

[0115] Optionally, before the non-target model starts to occupy the available processing resources, if the target model cannot generate the target output based on the target input, the target model and the non-target model will occupy the available processing resources at the same time. In this case, the second sub-information indicates that the longer the available processing resources are occupied by the non-target model, the longer the first time is; the second sub-information indicates that the greater the proportion of available processing resources occupied by the non-target model, the smaller the proportion of available processing resources occupied by the target model, and the longer the first time is; the second sub-information indicates that the higher the priority of the non-target model, the greater the proportion of available processing resources occupied by the non-target model, the smaller the proportion of available processing resources occupied by the target model, and the longer the first time is.

[0116] Optionally, before the non-target model starts to occupy available processing resources, if the target model is able to generate a target output based on the target input, the first time that the target model generates a target output based on the target input is determined based on the currently available processing resources (i.e., if an application is occupying the processing resources, the application currently occupying the processing resources is not paused, and the target model only occupies part of the processing resources of the electronic device).

[0117] Optionally, before the non-target model starts to occupy the available processing resources, if the target model that occupies all the processing resources of the electronic device (i.e., if an application is occupying the processing resources, the application currently occupying the processing resources is paused) can generate the target output based on the target input, then the first time that the target model generates the target output based on the target input is determined based on all the processing resources of the electronic device. This way, the time to obtain the target output is shorter. In this case, interactive information can also be output to ask the input object whether it agrees to occupy all the processing resources of the electronic device to generate the target output before the non-target model starts to occupy the processing resources. If the input object chooses to agree, the application currently occupying the processing resources is paused, and all the processing resources of the electronic device are occupied to run the target model, so that the target model quickly generates the target output based on the target input; if the input object chooses not to agree, the application currently occupying the processing resources continues to run, and the first time is determined based on the first two methods.

[0118] Step S303: outputting the second information. The second information carries the first time determined based on the second sub-information.

[0119] like Figure 3b As shown, another interactive example diagram of an embodiment of the present application is provided, in which after obtaining the target input, the first information is obtained, and the second information is output based on the first information. In this example, the target input is "Help me sort out some mainstream opinions recently published by famous experts from the top 3 companies in the field of patent writing", and the second information is "Your question is more complicated. It is detected that you have a meeting in 15 minutes, but if you are willing to let me occupy all the resources of the machine, I can probably calculate the answer to your question in 10 minutes. Do you agree?".

[0120] In an optional embodiment, another implementation flowchart of obtaining the first information and outputting the second information based on the first information is as follows: Figure 4a As shown, this may include:

[0121] Step S401: Obtain third sub-information. The third sub-information represents the degree of understanding of the field to which the target input belongs by the input object.

[0122] The third sub-information is included in the first information, that is, the first information includes the third sub-information. The third sub-information may include, but is not limited to: the browsing history of the input object, the position of the input object, the years of work experience, etc. The browsing history indicates that the more information the input object browses in the field of the target input, the higher the understanding of the input object to the field of the target input; the higher the position of the input object, the higher the understanding of the field of the target input; the longer the years of work of the input object, the higher the understanding of the field of the target input.

[0123] Step S402: Determine the first time (ie, the time taken for the target model to generate the target output based on the target input) based on the third sub-information.

[0124] The higher the input object's understanding of the field to which the target input belongs, the more in-depth the response needs to be, that is, a higher quality response, which takes more time and the longer the first time; conversely, the shorter the first time.

[0125] Step S403: output the second information. The second information carries the first time determined based on the third sub-information.

[0126] In an optional embodiment, the first information includes at least one sub-information among the three sub-information of the first sub-information, the second sub-information and the third sub-information.

[0127] In the case where the first information includes at least two of the above three sub-information, the first time (i.e., the time taken for the target model to generate the target output based on the target input) can be determined by combining the at least two sub-information in the first information. The association between the first time and various sub-information can be referred to the above embodiments, which will not be repeated here.

[0128] like Figure 4b As shown, it is another interactive example diagram provided by the embodiment of the present application, in which after obtaining the target input, the first information is obtained, and the second information is output based on the first information. In this example, the target input is "Help me sort out some mainstream views recently published by famous experts in the top 3 companies in the field of patent writing", and the second information is "This question is more complicated. Considering that you are a practitioner in the patent field, I need to search and organize the relevant materials in depth, and reply to you in about 12 minutes."

[0129] In an optional embodiment, another implementation flowchart of obtaining the first information and outputting the second information based on the first information is as follows: Figure 5a As shown, this may include:

[0130] Step S501: Obtain fourth sub-information.

[0131] The fourth sub-information is included in the first information, that is, the first information includes the fourth sub-information. The fourth sub-information is related to the input object and / or the input environment.

[0132] Optionally, the fourth sub-information related to the input object can characterize the personality of the input object. As an example, the fourth sub-information can include: a user portrait determined based on the daily behavior of the input object, which characterizes whether the input object is patient. For example, after inputting information, the input object often performs other operations before the target output is fully displayed; or, while waiting for the target output, the input object often shakes the mouse aimlessly, or clicks the mouse, etc. These behaviors indicate that the input object has an impatient personality. In this case, an impatient label can be added to the user portrait to characterize the user's impatient personality.

[0133] Optionally, the fourth sub-information related to the input environment may include: the time and location where the input object is currently located.

[0134] Step S502: Determine a second time based on the fourth sub-information. The second time represents the time the input object can wait.

[0135] Optionally, if the input object is impatient, the input object can wait for a shorter time; if the input object is patient, the input object can wait for a longer time.

[0136] If the input object is currently in the first target time period (e.g., 9:00-22:00) and is at the first target location (e.g., company), it is considered that the input object is still working and hopes to obtain the target output quickly, so the input object can wait for a relatively short time.

[0137] For example, if the current time of the input object is not within the first target time period, and the location is the second target location (eg, home), it is considered that the input object may be going to sleep and can wait for a longer time.

[0138] Step S503: output second information based on the first time and the second time. The second information is also used to prompt the input object to trigger the target model to run or perform other tasks.

[0139] That is, before the target model generates the target output based on the target input, the present application not only obtains the first time that the target model generates the target output based on the target input, but also obtains the second time that the input object can wait.

[0140] The output second information prompts the input object to trigger the target model to run so as to output the target output at the second time or the third time, or prompts the input object to perform other tasks while prompting the first time for obtaining the target output.

[0141] The input object can perform other tasks through the electronic device (for example, continue to use the electronic device, at which time the target model will simultaneously generate the target output based on the target input in the background), or can perform other tasks without using the electronic device (for example, sleeping, reading, exercising, etc.).

[0142] like Figure 5b As shown, it is another interactive example diagram provided by the embodiment of the present application, in which after obtaining the target input, the first information is obtained, and the second information is output based on the first information. In this example, the target input is "Help me sort out some mainstream opinions recently published by famous experts in the top 3 companies in the field of patent writing", and the second information is "The question you asked is very complicated. I need enough time. Now it seems that you are going to sleep. Can I tell you the answer tomorrow morning?".

[0143] When the fourth sub-information represents that the input object has a patient personality, the second information prompts the input object to trigger the target model to run so as to output the target output within a second time.

[0144] In the case where the fourth sub-information indicates that the input object has an impatient personality and the time the input object can wait is less than the duration threshold, the second information prompts the input object to trigger the target model to run to output the target output within a third time. The third time is determined based on the second time, the third time is greater than the second time, and the difference between the third time and the second time is less than the preset difference. Because the input object has an impatient personality, if the second information prompts the input object to trigger the target model to run to output the target output within the second time, when the input object's waiting time is about to reach the second time, the input object may not be able to wait to see the output result, but at this time, the complete result has not yet been output. If the second information prompts the input object to trigger the target model to run to output the target output within the third time, the target output may be obtained before the input object's waiting time reaches the third time, thereby improving the user experience.

[0145] In an optional embodiment, if the first information includes third sub-information, the third sub-information represents the input object's understanding of the field to which the target input belongs. When the input object's understanding of the field to which the target input belongs meets the second condition, the third information can be output based on the first time, and the third information is used to prompt the input object to select a knowledge base.

[0146] As an example, the input object's understanding of the field to which the target input belongs satisfying the second condition may include: the input object's understanding of the field to which the target input belongs is greater than a threshold value.

[0147] If the input object's understanding of the field to which the target input belongs meets the second condition, it means that the input object has a relatively high understanding of the field to which the target input belongs and is a professional in the field to which the target input belongs. It is necessary to provide a target output with more in-depth content. To provide a target output with more in-depth content, it is necessary to refer to more and more professional knowledge bases, and more professional knowledge bases may require payment. At this time, the third information can be output to ask the input object whether to pay to choose a more professional knowledge base.

[0148] like Figure 6 As shown, it is an interactive example diagram provided by the embodiment of the present application, which obtains the first information after obtaining the target input, and outputs the third information based on the first information. In this example, the target input is "Help me sort out some mainstream views recently published by famous experts in the top 3 companies in the field of patent writing", and the third information is "This question is more complicated. Considering that you are a practitioner in the patent field, I need to search and organize the relevant materials in depth. If you allow me to use the paid knowledge base, I can give a higher quality answer. Do you want to use the paid knowledge base?".

[0149] Furthermore, if the user chooses to pay for a more professional knowledge base, the target model will refer to the more professional knowledge base when generating the target output based on the target input; otherwise, the more professional knowledge base will not be referred to.

[0150] Another implementation flow chart of the data processing method provided in the embodiment of the present application is as follows: Figure 7a As shown, this may include:

[0151] Step S701: Obtain target input.

[0152] The target input is the interactive content input by the input object (eg, user), which may include but is not limited to content in at least one of the following formats: text, file, image, etc.

[0153] Step S702: If the target input meets the first condition, obtain first information. The first information is related to the input object.

[0154] The first condition is used to determine whether personalized output is required for the input object.

[0155] Optionally, the target input satisfies the first condition may include: the target input is a complex question. For details on how to determine whether the target input is a complex question, please refer to the above embodiments, which will not be described in detail here.

[0156] Optionally, the first information may include characteristic information of the input object and / or the environment in which the input object is located. The characteristic information of the input object may include, but is not limited to, at least one of the following: identity information, personality, browsing history, position, years of work, etc., or other characteristics of the input object. The environment in which the input object is located may include, but is not limited to, at least one of the following: time, location, etc.

[0157] Step S703: output fourth information based on the first information. The fourth information includes the first output or the second output, the first output or the second output is generated by the target model based on the target input, and the first output is different from the second output.

[0158] That is, the first information obtained is different, and the fourth information generated by the target model based on the target input is different.

[0159] Optionally, a knowledge source may be determined based on the first information, and relevant knowledge may be searched in the determined knowledge source according to the target input, and the target model may generate fourth information based on the target input according to the searched relevant knowledge.

[0160] Depending on the first information, the determined knowledge source may be different. When the determined knowledge source is different, the searched related knowledge is different. Therefore, the fourth information generated by the target model based on the target input according to the searched related knowledge is also different.

[0161] Optionally, relevant knowledge can be searched in a preset knowledge source according to the target input (that is, no matter what the first information is, relevant knowledge is searched in the same knowledge source), and the target model generates fourth information based on the target input according to the searched relevant knowledge and the first information. Based on this, when the first information is different, the fourth information generated by the target model based on the target input according to the searched relevant knowledge and the first information is different.

[0162] The data processing method provided in the embodiment of the present application obtains first information related to the input object after obtaining the target input, if the target input satisfies the first condition, and outputs fourth information based on the first information, wherein the fourth information includes a first output or a second output, and the first output or the second output is generated by the target model based on the target input, and the first output is different from the second output. That is to say, the present application obtains different outputs according to the difference of the first information related to the input object, changes the output mode, and enables the input object to obtain personalized output associated with the first information, increases the interaction mode with the input object, improves the intelligence of the data processing system based on the large model, and meets the input object's demand for intelligent interaction.

[0163] In an optional embodiment, an implementation manner of outputting the fourth information based on the first information may include:

[0164] If the first information indicates that the input object is the first input object, the output includes fourth information of the first output. Figure 7b As shown, it is an interactive example diagram provided by an embodiment of the present application, in which after obtaining the target input of the first input object A, the first information is obtained, and the fourth information is output based on the first information. In this example, the target input is "Help me sort out some mainstream opinions recently published by famous experts in the top 3 companies in the field of patent writing", and the first output is "In the field of patent writing, the top companies usually include some...".

[0165] If the first information characterizes that the input object is the second input object, the output includes fourth information of the second output. The first input object is different from the second input object. Figure 7c As shown, it is another interactive example diagram provided by the embodiment of the present application, in which after obtaining the target input of the second input object B, the first information is obtained, and the fourth information is output based on the first information. In this example, the target input is "Help me sort out some mainstream views recently published by famous experts in the top 3 companies in the field of patent writing", and the second output is "Understanding the mainstream points in the patent field can better understand the importance and commercial value of intellectual property rights...".

[0166] That is to say, when different input objects input the same target input, first information associated with different input objects is obtained, and the first information associated with different input objects is usually different. Therefore, the target output generated by the target model based on the target input is different.

[0167] Optionally, an implementation manner of outputting the fourth information based on the first information may include:

[0168] If the first information represents the time that the input object can wait and satisfies the second condition, the output includes the fourth information of the first output. The quality of the first output is higher than the quality of the second output. Figure 7d As shown, another interactive example diagram provided by an embodiment of the present application is to obtain the first information after obtaining the target input of the first input object A, and output the fourth information based on the first information. In this example, the target input is "Why does global climate change lead to an increase in extreme weather events?", and the first output is "Global climate change is a complex and multidimensional issue, which involves..." In this example, the first input object A has enough time to wait for the model to generate an answer, so the content of the first output is relatively rich and profound.

[0169] If the waiting time of the input object satisfies the second condition, it means that the waiting time of the input object is relatively long, and the target model has more time to generate high-quality output; if the waiting time of the input object does not meet the second condition, it means that the waiting time of the input object is relatively short, and the target model does not have enough time to generate high-quality output, and can only obtain low-quality output. Figure 7e As shown, it is another interactive example diagram provided by the embodiment of the present application, which obtains the first information after obtaining the target input of the first input object A, and outputs the fourth information based on the first information. In this example, the target input is "Why does global climate change lead to an increase in extreme weather events?", and the second output is "Considering that you have a meeting in 5 minutes, for your convenience, the following is given...". In this example, the first input object A only has a few minutes to wait for the model to generate an answer, so the content of the second output is relatively brief.

[0170] That is, if the first information associated with the first input object represents the time the first input object can wait and satisfies the second condition, and the first information associated with the second input object represents the time the second input object can wait and does not satisfy the second condition, then the quality of the first output is higher than the quality of the second output.

[0171] Alternatively, if the first information associated with the first input object represents that the time the first input object can wait satisfies the second condition, the output includes fourth information of the first output; if the first information associated with the first input object represents that the time the first input object can wait does not satisfy the second condition, the output includes fourth information of the second output; the quality of the first output is higher than the quality of the second output.

[0172] Optionally, an implementation manner of outputting the fourth information based on the first information may include:

[0173] If the first information represents the degree of understanding of the target input field by the input object and satisfies the third condition, the output includes the fourth information of the first output. The quality of the first output is higher than the quality of the second output. Figure 7f As shown, another interactive example diagram provided by an embodiment of the present application is to obtain the first information after obtaining the target input input by the input object, and output the fourth information based on the first information. In this example, the target input is "In an international commercial dispute involving the laws of multiple countries, how to determine the applicable law and jurisdiction?", and the first output is "In international commercial disputes involving the laws of multiple countries, determining the law and jurisdiction to use is a complex and important issue. The following are some specific methods and suggestions based on knowledge and practical experience in the legal field...". In this example, the input object is a practitioner in the legal field, so the answer given is relatively rich in content (some of the content is omitted due to space limitations) and of relatively high quality.

[0174] If the input object's understanding of the target input field meets the third condition, it means that the input object is an expert in the target input field and needs to give a more in-depth output; if the input object's understanding of the target input field does not meet the third condition, it means that the input object has little understanding of the target input field and needs to give a simple and easy-to-understand output. Figure 7g As shown, another interactive example diagram provided by an embodiment of the present application is to obtain the first information after obtaining the target input input by the input object, and output the fourth information based on the first information. In this example, the target input is "In an international commercial dispute involving the laws of multiple countries, how to determine the applicable law and jurisdiction?", and the second output is "In international commercial disputes, since the laws of multiple countries are involved, determining the law and jurisdiction to be used is a complex but crucial process. The following are some basic guiding principles and methods..." In this example, the input object is not a practitioner in the legal field and has little knowledge of legal knowledge, so the answer given is simple in content (some of the content is omitted due to space limitations) and of relatively low quality.

[0175] That is to say, if the first information associated with the first input object represents the first input object's understanding of the field to which the target input belongs, which satisfies the third condition, and the first information associated with the second input object represents the second input object's understanding of the field to which the target input belongs, which does not satisfy the third condition, then the quality of the first output is higher than the quality of the second output.

[0176] In an optional embodiment, another implementation manner of outputting the fourth information based on the first information may include:

[0177] If the first information indicates that the input object is the first input object and is in the first scene, the output includes fourth information of the first output. Figure 7d shown.

[0178] If the first information indicates that the input object is the first input object and is in the second scene, the output includes the fourth information of the second output. The first scene is different from the second scene. Figure 7e shown.

[0179] That is, when the same input object inputs a target input in different scenarios, if different first information associated with the input object is obtained, the target output generated by the target model based on the target input will be different.

[0180] The first scene and the second scene can be different input environments where the input object is located. For example, the first scene is when the input object is in the first target time period (for example, 9:00-22:00) and the location is the first target location (for example, the company); the second scene is when the input object is in a non-first target time period (for example, 22:00 to 9:00 the next day) and the location is a non-first target location (for example, home).

[0181] When the input object is in different scenes, the time that the input object can wait may be different, and thus the quality of the first output and the quality of the second output determined are different.

[0182] In an optional embodiment, when outputting the fourth information based on the first information, the method may further include:

[0183] outputting fifth information and / or sixth information;

[0184] The fifth information includes at least one source data and an associated display relationship between the source data and the output included in the fourth information. The source data may include but is not limited to at least one of the following data: articles, software (also called applications), knowledge base, etc.

[0185] That is to say, while outputting the fourth information, the source data referenced when the output target model generates the target output (first output or second output) based on the target input is also associated. The association between the fourth information and the source data may include but is not limited to: the association between each fragment in the fourth information and the source data.

[0186] Furthermore, after obtaining a selection instruction for any segment in the fourth information, source data associated with the segment is highlighted so that the input object knows that the segment selected by the input object is generated based on the highlighted source data.

[0187] The sixth information includes source data with an identifier, where the identifier indicates that the input object is associated with the source data. Figure 7h As shown, it is an example diagram of outputting the sixth information provided by an embodiment of the present application. In this example, 5 documents are referenced when obtaining the fourth information, among which the second document "2.COP26 | Interpretation of Climate Report: Extreme Weather Events Are an Important Threat to Global Warming" is associated with an eye pattern Characterizes whether the input object has viewed this document.

[0188] That is to say, if there is source data associated with the input object in at least one source data, for example, source data browsed by the input object, or source data created by the input object, then when the source data associated with the input object is output, an identifier is added to the source data so that the input object knows that it is associated with the source data with the identifier.

[0189] As an example, if the association relationship between the input object and the source data is different, the identifier of the source data may also be different. For example, if the source data has a first identifier, it indicates that the input object has browsed the source data; if the source data has a second identifier, it indicates that the source data was created by the input object.

[0190] In an optional embodiment, another implementation flow chart of the data processing method provided by the present application is as follows: Figure 8 As shown, this may include:

[0191] Step S801: Obtain target input.

[0192] The target input is the interactive content input by the input object (eg, user), which may include but is not limited to content in at least one of the following formats: text, file, image, etc.

[0193] Step S802: If the target input satisfies the first condition, first information is obtained.

[0194] The first condition is used to determine whether an output policy needs to be selected.

[0195] Optionally, the target input satisfies the first condition may include: the target input is a complex question. For details on how to determine whether the target input is a complex question, please refer to the above embodiments, which will not be described in detail here.

[0196] Optionally, the first information may include: information related to at least one of an input object, an input environment, and an electronic device.

[0197] Optionally, the information related to the input object and / or the input environment may include but is not limited to at least one of the following: identity information, personality, time, location, browsing history, position, years of work, etc. or other characteristics of the input object.

[0198] The information related to the electronic device may include but is not limited to at least one of the following: the number of cores, main frequency and cache size of the processor, memory capacity and frequency, hard disk type and storage capacity, video memory size, number of stream processors, bus width, software performance, etc.

[0199] Step S803: Determine a target strategy based on the first information.

[0200] First, the information is different, and the target strategy determined is different.

[0201] The target strategy represents the strategy used to generate the target output, including any of the following:

[0202] Selecting a model matching the first information from among a plurality of models as a target model according to the first information, and generating a target output based on the target model;

[0203] Determine the number of calls to the target model according to the first information;

[0204] Determine, according to the first information, a step of generating a target output based on a target input by a target model;

[0205] Determining, according to the first information, the depth of information search in a preset information source (e.g., a website, or a free knowledge base, etc.) or a selected knowledge base based on the target input;

[0206] The extent of information search in a preset information source or a selected knowledge base based on the target input is determined according to the first information.

[0207] Among them, any two models among the several models are different models, and the difference between the models may include at least one of the following aspects: different publishers of the models, different types of models (for example, a model that is good at summarization, a model that is good at reasoning, a model that is good at classification, etc.), different versions of the models, etc.

[0208] According to the preset correspondence between the first information and the model, the model corresponding to the acquired first information among the multiple models may be used as the model matching the first information, ie, the target model.

[0209] Alternatively, each of the several models can be used as a category to classify the first information to determine which model of the several models the first information belongs to, and the category to which the determined first information belongs is determined as the model matching the first information, namely, the target model.

[0210] Alternatively, the time that the input object can wait and / or the input object's degree of understanding of the field to which the target input belongs can be determined based on the first information, and based on the correspondence between the pre-set waiting time and / or the degree of understanding of the field to which the target input belongs and the model, the model corresponding to the time that the input object can wait and / or the input object's degree of understanding of the field to which the target input belongs is determined as the model that matches the first information, i.e., the target model.

[0211] Alternatively, the needs of the input object are first determined based on the target input, and after determining the time the input object can wait and / or the input object's degree of understanding of the field to which the target input belongs based on the first information, in the model that can realize the needs of the input object, based on the correspondence between the pre-set waiting time and / or the degree of understanding of the field to which the target input belongs and the model, the model corresponding to the time the input object can wait and / or the input object's degree of understanding of the field to which the target input belongs is determined as the model that matches the first information, i.e., the target model.

[0212] There can be only one target model or multiple target models. In the case of multiple target models, the multiple target models can be models of the same type from different publishers, or models of the same type with different versions. Each model can generate a target output based on the target input, and then the final target output is selected from the target outputs generated by different target models, or the target outputs generated by different target models can be fused to obtain the final target output.

[0213] Optionally, after determining the target model, the depth of the algorithm for generating the target output based on the target input by the target model can also be determined according to the first information, that is, the number of calls to the target model. As an example, if the first information represents that the input object can wait longer or the input object has a higher degree of understanding of the field to which the target input belongs, the target model can be called more times to give a more accurate and deeper output; otherwise, the target model can be called less times to give a more accurate and easy-to-understand output.

[0214] Optionally, after determining the target model, the steps for the target model to generate the target output based on the target input can also be determined based on the first information. For example, the number of steps for the target model to generate the target output based on the target input is determined. As an example, the number of steps for the target model to generate the target output based on the target input can be determined based on the behavioral data of the input object. For example, the input object wants the big model to help recommend a hot pot restaurant. The general process is that the big model determines the user needs based on the target input, then collects relevant information, and then selects the hot pot restaurant that meets the needs of the input object based on the collected relevant information and recommends it to the input object. In the present application, if the input object is determined to be interested in a certain hot pot restaurant based on its behavior before asking the big model a question, for example, the input object has browsed a certain software and viewed a certain hot pot restaurant multiple times in the software, or the chat record indicates that the input object is interested in a certain hot pot restaurant, then the big model does not need to collect relevant information and can directly recommend the hot pot restaurants that the input object has viewed multiple times or the hot pot restaurants mentioned in the chat records to the input object; if the input object has not browsed any software before asking the big model a question, or the chat record does not reflect an interest in any hot pot restaurant, the user's needs can be determined based on the target input, and then relevant information can be collected, and then a hot pot restaurant that meets the input object's needs can be selected based on the collected relevant information and recommended to the input object.

[0215] Optionally, after determining the target model, the depth of information search in the preset information source or the knowledge base selected by the input object based on the target input is determined according to the first information. For example, if the first information indicates that the input object has a relatively high degree of understanding of the field to which the target input belongs, the depth of information search in the preset information source or the knowledge base selected by the input object based on the target input can be increased; otherwise, the depth of information search in the preset information source or the knowledge base selected by the input object based on the target input is reduced.

[0216] Optionally, after determining the target model, the breadth of information search in the preset information source or the knowledge base selected by the input object based on the target input is determined according to the first information. For example, if the first information represents that the knowledge of the input object involves multiple fields, the breadth of information search in the preset information source or the knowledge base selected by the input object based on the target input can be increased; otherwise, the breadth of information search in the preset information source or the knowledge base selected by the input object based on the target input is reduced.

[0217] The data processing method provided by the present application obtains the first information after obtaining the target input, if the target input satisfies the first condition, and determines the target strategy based on the first information. The target strategy is a strategy that characterizes the strategy used to generate the target output. In other words, the present application determines different strategies for generating the target output according to the different first information, changes the output mode of the target output, enables the input object to obtain the personalized output associated with the first information, increases the interaction mode with the input object, and meets the input object's demand for intelligent interaction.

[0218] The present application also provides an electronic device in an embodiment. Fig. 9 As shown, it shows a structural schematic diagram of an electronic device suitable for implementing the method embodiment of the present application. Fig. 9 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0219] like Fig. 9 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 into a random access memory (RAM) 903. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 903. The processing device 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0220] Typically, the following devices may be connected to the I / O interface 905: an input device 906 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 908 including, for example, a memory card, a hard disk, etc.; and a communication device 909. The communication device 909 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Fig. 9 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0221] The processing device 901 included in the electronic device is used to output the second information, and the second information is used to prompt the first time of obtaining the target output; the processing device 901 is also used to provide an environment for running the target model so that the target model generates the target output based on the target input. Specifically, when the processing device 901 outputs the second information, it is used to: obtain the target input; if the target input meets the first condition, obtain the first information; output the second information based on the first information

[0222] And / or, the electronic device includes a processing device 901 for obtaining a target input; if the target input satisfies a first condition, obtaining first information; the first information is related to the input object; fourth information is output based on the first information; the fourth information includes a first output or a second output, the first output or the second output is generated by a target model based on the target input, and the first output is different from the second output.

[0223] And / or, the processing device 901 included in the electronic device is used to obtain a target input; if the target input satisfies a first condition, obtain first information; determine a target strategy based on the first information; the target strategy represents a strategy for generating a target output, including any of the following:

[0224] Selecting a model matching the first information from among a plurality of models as a target model according to the first information, and generating a target output based on the target model;

[0225] Determining the number of calls to the target model according to the first information;

[0226] Determine, according to the first information, a step of generating the target output by the target model based on the target input and the target information;

[0227] Determining, according to the first information, a depth of information search in the preset information source or the selected knowledge base based on the target input;

[0228] The extent of information search in the preset information source or the selected knowledge base based on the target input is determined according to the first information.

[0229] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any data processing method provided in the embodiment of the present application.

[0230] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any data processing method provided in the embodiment of the present application.

[0231] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0232] It should be understood that in the embodiments of the present application, the various embodiments and features can be combined with each other to solve the aforementioned technical problems.

[0233] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the technology can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0234] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product. Professionals and technicians may use different methods to implement the described functions for each specific solution, but such implementation should not be considered beyond the scope of this application.

[0235] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0236] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0237] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing method, the method comprising: Get target input; If the target input satisfies a first condition, obtaining first information; outputting second information based on the first information, where the second information is used to prompt a first time of obtaining a target output; The target output is generated by a target model based on the target input, and the first time is related to the first information.

2. The method according to claim 1, wherein obtaining the first information and outputting the second information based on the first information comprises any one of the following: Obtaining first sub-information, determining the first time based on the first sub-information, and outputting the second information; the first sub-information represents the processing performance of the electronic device running the target model; obtaining second sub-information, determining the first time based on the second sub-information, and outputting the second information; The second sub-information represents the occupation of available processing resources of the electronic device by non-target models; Obtaining third sub-information, determining the first time based on the third sub-information, and outputting the second information; the third sub-information represents the degree of understanding of the field to which the target input belongs by the input object; The first information includes first sub-information, second sub-information and / or third sub-information.

3. The method according to claim 1 or 2, wherein obtaining the first information and outputting the second information based on the first information comprises: Obtaining fourth sub-information, where the fourth sub-information is related to the input object and / or the input environment; determining a second time based on the fourth sub-information, the second time representing a time that the input object can wait; The second information is output based on the first time and the second time; the second information is also used to prompt the input object to trigger the target model to run or perform other tasks.

4. The method according to claim 1, if the first information includes the third sub-information, the method comprises: Determining, based on the third sub-information, the degree of understanding of the field to which the target input belongs by the input object; If the input object's understanding of the field to which the target input belongs meets a second condition, third information is output based on the first time, and the third information is used to prompt the selection of a knowledge base.

5. A data processing method, the method comprising: Get target input; If the target input satisfies a first condition, obtaining first information; The first information is related to the input object; output fourth information based on the first information; The fourth information includes a first output or a second output, wherein the first output or the second output is generated by a target model based on the target input, and the first output is different from the second output.

6. The method according to claim 5, outputting fourth information based on the first information, comprising any one of the following: If the first information indicates that the input object is a first input object, the output includes fourth information of the first output; if the first information indicates that the input object is a second input object, the output includes fourth information of the second output; the first input object is different from the second input object; If the first information represents that the input object is the first input object and is in the first scene, the output includes the fourth information of the first output; if the first information represents that the input object is the first input object and is in the second scene, the output includes the fourth information of the second output; the first scene is different from the second scene.

7. The method according to claim 5, outputting fourth information based on the first information, comprising any one of the following: If the first information represents that the time during which the input object can wait satisfies the second condition, outputting fourth information including the first output; If the first information represents that the degree of understanding of the input object about the field to which the target input belongs satisfies a third condition, outputting fourth information including the first output; The quality of the first output is higher than the quality of the second output.

8. The method according to any one of claims 5 to 7, when outputting fourth information based on the first information, further comprising: outputting fifth information and / or sixth information; The fifth information includes at least one source data and an associated display relationship between the source data and the output included in the fourth information; The sixth information includes source data with an identifier, wherein the identifier indicates that the input object is associated with the source data.

9. A data processing method, the method comprising: Get target input; If the target input satisfies a first condition, obtaining first information; determining a target strategy based on the first information; The target strategy represents a strategy for generating a target output, including any of the following: Selecting a model matching the first information from among a plurality of models as a target model according to the first information, and generating a target output based on the target model; Determining the number of calls to the target model according to the first information; Determine, according to the first information, a step of generating the target output by the target model based on the target input and the target information; Determining, according to the first information, a depth of information search in a preset information source or a selected knowledge base based on the target input; The extent of information search in the preset information source or the selected knowledge base based on the target input is determined according to the first information.

10. An electronic device, comprising at least one processor, the processor being used to output second information, the second information being used to prompt a first time of obtaining a target output; The processor is further configured to provide an environment for running a target model so that the target model generates the target output based on a target input.

Images