Information processing method and device, electronic equipment and storage medium

Abstract

The invention relates to an information processing method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the target demand information of a target user, and enabling the target demand information to indicate the demand of the target user; performing intention recognition on the target demand information to obtain a target intention corresponding to the target user; determining a target large language model from a plurality of preset large language models deployed in the electronic equipment according to the target intention; and calling the target large language model through the target calling interface so as to process the target demand information by utilizing the target large language model. According to the method and the device, the cost of connecting the large language model by the user is reduced, and the accuracy of selecting the large language model by the user and the use experience of the user are improved.

Description

Technical Field

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

[0002] Large language models are widely used in natural language processing, computer vision, speech recognition and other fields. At present, various large language models are emerging one after another, so users need to select a suitable large language model from multiple existing large language models when using them. However, due to the large number of existing large language models and the subjectivity of user selection, users may choose the wrong large language model. In addition, the API call interfaces of the existing large language models are different, which makes it costly for users to connect to a new large language model each time, which in turn affects the user experience. Summary of the invention

[0003] In view of this, in order to solve the above-mentioned technical problems or part of the technical problems, the embodiments of the present application provide an information processing method, device, electronic device and storage medium.

[0004] In a first aspect, the present application provides an information processing method, which is applied to an electronic device, wherein a plurality of preset large language models are deployed in the electronic device, and the electronic device has a target calling interface, and the method comprises:

[0005] Acquire target demand information of a target user, wherein the target demand information indicates the demand of the target user;

[0006] Performing intent recognition on the target demand information to obtain the target intent corresponding to the target user;

[0007] According to the target intent, determining a target large language model from a plurality of the preset large language models deployed in the electronic device;

[0008] The target large language model is called through the target calling interface to process the target demand information using the target large language model.

[0009] In an optional implementation, before executing the step of determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent, the method further includes:

[0010] Acquire a balance in a target account corresponding to the target user, where the target account is pre-created by the target user in the electronic device, and the balance in the target account is used to pay for the fee of the preset large language model among the plurality of preset large language models that require payment for use;

[0011] The step of determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent includes:

[0012] According to the target intent and the balance in the target account, a target large language model is determined from a plurality of the preset large language models deployed in the electronic device.

[0013] In an optional implementation, determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent and the balance in the target account includes:

[0014] According to the target intent, determining a first candidate large language model set from a plurality of the preset large language models deployed in the electronic device;

[0015] When the first candidate large language model set includes at least two first candidate large language models, determining a preset fee corresponding to each of the first candidate large language models, where the preset fee indicates a fee to be paid for using the first candidate large language model;

[0016] Determine the minimum preset fee from the preset fees corresponding to all the first candidate large language models in the first candidate large language model set;

[0017] When the balance in the target account is greater than or equal to the minimum preset fee, the first candidate large language model corresponding to the minimum preset fee is determined as the target large language model.

[0018] In an optional implementation, after executing the step of determining the minimum preset fee from the preset fees corresponding to all the first candidate large language models in the first candidate large language model set, the method further includes:

[0019] When the balance in the target account is less than the minimum preset fee, generating an alarm prompt message according to the first candidate large language model corresponding to the minimum preset fee;

[0020] The alarm prompt information is pushed to the target terminal where the target user is located.

[0021] In an optional implementation, after executing the step of determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent, the method further includes:

[0022] Determining a target number of the target large language models;

[0023] When the number of the targets is at least two, determining a target calling order between the determined target large language models according to the target intention;

[0024] The calling of the target large language model through the target calling interface to process the target demand information using the target large language model includes:

[0025] Each of the target large language models is called in sequence through the target calling interface according to the target calling order, so as to process the target demand information using each of the target large language models.

[0026] In an optional implementation, before executing the step of determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent, the method further includes:

[0027] Obtaining target evaluation information corresponding to each of the preset large language models deployed in the electronic device, the target evaluation information being used to indicate the target user's evaluation of a processing result obtained by the preset large language model processing the target user's demand information, the target evaluation information including a target evaluation score;

[0028] The step of determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent includes:

[0029] Determining a second candidate large language model set from a plurality of the preset large language models deployed in the electronic device according to the target intent;

[0030] When the second candidate large language model set includes at least two second candidate large language models, determining the second candidate large language model corresponding to the highest target evaluation score from the second candidate large language model set;

[0031] The second candidate large language model corresponding to the highest target evaluation score is determined as the target large language model.

[0032] In an optional embodiment, the method further includes:

[0033] In the process of processing the target demand information by using the target large language model, obtaining target indicator information corresponding to the target large language model, wherein the target indicator information is used to reflect the stability of the target large language model;

[0034] When it is determined according to the target indicator information that the target large language model is unstable, determining a backup large language model corresponding to the target large language model;

[0035] The standby large language model is called through the target calling interface to process the target demand information using the standby large language model.

[0036] In a second aspect, the present application provides an information processing device, which is applied to an electronic device, wherein a plurality of preset large language models are deployed in the electronic device, and the electronic device has a target calling interface, wherein the device comprises:

[0037] An acquisition module, used to acquire target demand information of a target user, wherein the target demand information indicates the demand of the target user;

[0038] An identification module, used to perform intent identification on the target demand information to obtain the target intent corresponding to the target user;

[0039] A determination module, configured to determine a target large language model from a plurality of the preset large language models deployed in the electronic device according to the target intent;

[0040] A processing module is used to call the target large language model through the target calling interface to process the target demand information using the target large language model.

[0041] In a third aspect, the present application provides an electronic device, comprising: a processor and a memory, wherein the processor is used to execute an information processing program stored in the memory to implement the information processing method as described above.

[0042] In a fourth aspect, the present application also provides a storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the information processing method as described above.

[0043] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art. The method provided by the embodiment of the present application is applied to an electronic device, in which a plurality of preset large language models are deployed, and the electronic device has a target calling interface. The method includes: obtaining target demand information of a target user, where the target demand information indicates the demand of the target user; performing intent recognition on the target demand information to obtain a target intent corresponding to the target user; determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent; and calling the target large language model through the target calling interface to process the target demand information using the target large language model. Through the above method, in order to enable users to connect to different preset large language models, the embodiment of the present application sets a target calling interface for calling different preset large language models in the electronic device, so that when the target demand information of the target user is obtained, the target intention corresponding to the target demand information is determined, and then according to the target intention, the target large language model for processing the target demand information is determined from the multiple preset large language models deployed in the electronic device, and then the target large language model is called through the target calling interface to use the target large language model to realize the processing of the target demand information, thereby reducing the cost of users connecting to the large language model and improving the accuracy of users' selection of large language models and users' usage experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0047] Figure 1 A flowchart of an information processing method provided in an embodiment of the present application;

[0048] Figure 2 A flowchart of another information processing method provided in an embodiment of the present application;

[0049] Figure 3A flowchart of another information processing method provided in an embodiment of the present application;

[0050] Figure 4 A flowchart of another information processing method provided in an embodiment of the present application;

[0051] Figure 5 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application;

[0052] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0053] In the above attached figure:

[0054] 10. Acquisition module; 20. Recognition module; 30. Determination module; 40. Processing module;

[0055] 600, electronic device; 601, processor; 602, memory; 6021, operating system; 6022, application; 603, user interface; 604, network interface; 605, bus system. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0057] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0058] refer to Figure 1 , Figure 1 A flowchart of an information processing method provided in an embodiment of the present application. An information processing method provided in an embodiment of the present application comprises the following steps:

[0059] S101: Obtain target demand information of target users.

[0060] In this embodiment, the method is applied to an electronic device, which is deployed with multiple preset large language models, and the electronic device has a target calling interface. The target calling interface is an API interface, through which any preset large language model deployed in the electronic device can be called. The specific form of the preset large language model can be selected according to actual needs, and the specific form of the preset large language model is not limited in this embodiment.

[0061] The target demand information indicates the target user's demand. The target demand information can be input by the target user through the target terminal where the target user is located, so as to obtain the target demand information of the target user. For example, the target demand information can be to convert a certain audio into a picture.

[0062] S102: Perform intent recognition on the target demand information to obtain the target intent corresponding to the target user.

[0063] In this embodiment, in order to accurately obtain a preset large language model for processing target demand information from multiple preset large language models deployed by the electronic device, a deep learning model can be pre-trained to implement intent recognition of the target demand information according to the trained deep learning model. When training the deep learning model, multiple demand information and intents can be used as training samples, so as to implement a deep learning model for intent recognition of the target demand information using the training samples.

[0064] Among them, after training the deep learning model and obtaining the target demand information of the target user, the trained deep learning model can be used to perform intent recognition on the target demand information to obtain the target intention corresponding to the target user, so as to use the target intention to accurately obtain the preset large language model for processing the target demand information from multiple preset large language models deployed in the electronic device.

[0065] S103: Determine a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent.

[0066] In this embodiment, the correspondence between different intents and preset large language models can be preset. After obtaining the target intent corresponding to the target user, the above correspondence can be queried based on the target intent to obtain the preset large language model corresponding to the target intent, and the preset large language model corresponding to the target intent is determined as the target large language model. For example, when the target intent is fast response speed, the preset large language model with fast processing speed is preferentially selected. When the target intent is output type (text, image, video, etc.), the preset large language model that can output the corresponding output type is selected.

[0067] S104: calling the target large language model through the target calling interface to process the target demand information using the target large language model.

[0068] In this embodiment, after determining the target large language model from multiple preset large language models deployed in the electronic device, since the target calling interface can call each preset large language model deployed in the electronic device for use, the target large language model deployed in the electronic device can be called through the target calling interface to use the target large language model to complete the processing of the target demand information, thereby reducing the cost of the user connecting to the large language model, and by determining the target intent corresponding to the target user, the target large language model used to process the target demand information is determined through the target intent, thereby improving the accuracy of the user's selection of the large language model and the user's usage experience.

[0069] An information processing method provided by the present embodiment sets a target calling interface for calling different preset large language models in an electronic device in order to enable a user to connect to different preset large language models, so as to determine the target intent corresponding to the target demand information when the target demand information of the target user is obtained, thereby determining a target large language model for processing the target demand information from a plurality of preset large language models deployed in the electronic device according to the target intent, and then calling the target large language model through the target calling interface, so as to realize the processing of the target demand information by using the target large language model, thereby reducing the cost of the user connecting to the large language model and improving the accuracy of the user's selection of the large language model and the user's usage experience.

[0070] refer to Figure 2 , Figure 2 A flowchart of another information processing method provided in an embodiment of the present application. An information processing method provided in an embodiment of the present application comprises the following steps:

[0071] S201: Obtain target demand information of target users.

[0072] S202: Perform intent recognition on the target demand information to obtain the target intent corresponding to the target user.

[0073] Regarding the above-mentioned step S201 and step S202, step S201 is consistent with the above-mentioned step S101, and step S202 is consistent with the above-mentioned step S102. For details, please refer to the above-mentioned step S101 and step S102, which will not be described in detail in this embodiment.

[0074] S203: Obtain the balance in the target account corresponding to the target user.

[0075] In this embodiment, the target account is created in advance by the target user in the electronic device, and the balance in the target account is used to pay for the preset large language models that require payment for use among the multiple preset large language models.

[0076] Among them, the various preset large language models deployed in the electronic device are not free. Some preset large language models need to be paid for use. Therefore, in order to use the various preset large language models deployed in the electronic device, the target user usually creates a target account in the electronic device in advance, so that the target user can recharge the target account, so that when the target user uses the preset large language model deployed in the electronic device, he can pay for it through the balance in the target account.

[0077] Specifically, after obtaining the balance in the target account corresponding to the target user, the most cost-effective target large language model can be determined from multiple preset large language models deployed in the electronic device based on the target intention corresponding to the target user and the balance in the target account, so as to reduce the target user's expense expenditure and improve the target user's usage experience.

[0078] It should be noted that after using the balance in the target account to pay for the preset large language model, the corresponding fee will be automatically deducted from the balance in the target account.

[0079] S204: Determine a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent and the balance in the target account.

[0080] In this embodiment, after obtaining the balance in the target account corresponding to the target user, if it is determined based on the target intention that multiple preset large language models that meet the requirements for processing the target demand information are deployed in the electronic device, the balance in the target account can be used to select the most cost-effective preset large language model from multiple qualified preset large language models as the target large language model, so as to reduce the target user's expense expenditure and improve the target user's usage experience.

[0081] Among them, in step S204, according to the target intention and the balance in the target account, a target large language model is determined from a plurality of preset large language models deployed in the electronic device, specifically including:

[0082] According to the target intent, determining a first candidate large language model set from a plurality of preset large language models deployed in the electronic device;

[0083] When the first candidate large language model set includes at least two first candidate large language models, determining a preset fee corresponding to each first candidate large language model;

[0084] Determine a minimum preset fee from the preset fees corresponding to all first candidate large language models in the first candidate large language model set;

[0085] When the balance in the target account is greater than or equal to the minimum preset fee, the first candidate large language model corresponding to the minimum preset fee is determined as the target large language model.

[0086] In this embodiment, the preset fee indicates the fee required to use the first candidate large language model. Based on the correspondence between different intentions and preset large language models, all preset large language models used to process target demand information can be determined from multiple preset large language models deployed in the electronic device, so that all the obtained preset large language models are determined as the first candidate large language model set, and the preset large language model in the first candidate large language model set is regarded as the first candidate large language model.

[0087] Among them, after obtaining the first candidate large language model set, if the first candidate large language model set includes only one first candidate large language model, determine the preset fee corresponding to the first candidate large language model. When the balance in the target account is greater than or equal to the preset fee corresponding to the first candidate large language model, the first candidate large language model is determined as the target large language model; when the balance in the target account is less than the preset fee corresponding to the first candidate large language model, generate an alarm prompt information, and push the alarm prompt information to the target terminal where the target user is located, so that the target user recharges the target account, thereby ensuring that the target user can use the target large language model with the highest cost performance. It should be noted that the correspondence between different preset large language models and preset fees can be pre-set, so that after obtaining the first candidate large language model, the preset fee corresponding to the first candidate large language model is determined based on the above correspondence.

[0088] Specifically, after obtaining the first candidate large language model set, if the first candidate large language model set includes at least two first candidate large language models, the preset fees corresponding to each first candidate large language model in the first candidate large language model are determined. If the balance in the target account is greater than or equal to the above-mentioned minimum preset fee, it indicates that the balance in the target account satisfies the payment for the first candidate large language model with the highest cost performance, so the first candidate large language model corresponding to the minimum preset fee can be directly determined as the target large language model, so that the target user can select the target large language model with the highest cost performance, reducing the cost expenditure of the target user and improving the user experience of the target user.

[0089] More specifically, after executing the step of determining the minimum preset fee from the preset fees corresponding to all first candidate large language models in the first candidate large language model set, the information processing method provided by this embodiment further includes the following steps:

[0090] When the balance in the target account is less than the minimum preset fee, an alarm prompt message is generated according to the first candidate large language model corresponding to the minimum preset fee;

[0091] Push the alarm prompt information to the target terminal where the target user is located.

[0092] In this embodiment, when the balance in the target account is less than the minimum preset fee, it indicates that the balance in the target account does not meet the payment for the first candidate large language model with the highest cost performance. Therefore, in order to ensure that the target user can select the first candidate large language model with the highest cost performance, an alarm prompt message can be generated based on the first candidate large language model with the lowest preset fee, thereby pushing the alarm prompt message to the target terminal where the target user is located, so that the target user recharges the target account, thereby ensuring that the target user can use the target large language model with the highest cost performance. It should be noted that the target terminal can be a mobile phone, a computer, etc., and the specific form of the target terminal can be selected according to actual needs. The specific form of the target terminal is not limited in this embodiment. After the target user recharges the target account, it can return to execute step S201 to determine the target large language model with the highest cost performance from the multiple preset large language models deployed in the electronic device.

[0093] S205: calling the target large language model through the target calling interface to process the target demand information using the target large language model.

[0094] In this embodiment, step S205 is consistent with the above-mentioned step S104. For details, please refer to the above-mentioned step S104, which will not be described in detail in this embodiment.

[0095] In the process of processing the target demand information using the target large language model in step S205, the target indicator information corresponding to the target large language model is obtained;

[0096] When it is determined according to the target indicator information that the target large language model is unstable, determining a backup large language model corresponding to the target large language model;

[0097] The standby large language model is called through the target calling interface to process the target demand information using the standby large language model.

[0098] Specifically, the target indicator information is used to reflect the stability of the target large language model. The target indicator information can be selected according to actual needs, and the target indicator information corresponding to different preset large language models is not limited in this embodiment. After obtaining the target indicator information corresponding to the target large language model, it can be determined whether the target large language model is stable according to the target indicator information. When the target large language model is stable, the target large language model can continue to be used to process the target demand information. When the target large language model is unstable, the standby large language model corresponding to the target large language model can be determined according to the correspondence between the different preset large language models and the standby large language models set in advance, so as to switch to the standby large language model to process the target demand information to ensure the coherence and consistency of the target user experience. In the process of processing the target demand information by the standby large language model, the target indicator information corresponding to the target large language model is continued to be obtained. If the target large language model is determined to be stable according to the target indicator information, it is switched to the target large language model again to process the target demand information to provide the best service. It should be noted that the correspondence between the preset large language model and the standby large language model can be set according to actual needs, and the above correspondence is not specifically limited in this embodiment.

[0099] An information processing method provided by the present embodiment sets a target calling interface for calling different preset large language models in an electronic device in order to enable a user to connect to different preset large language models, so as to determine the target intent corresponding to the target demand information when the target demand information of the target user is obtained, thereby determining a target large language model for processing the target demand information from a plurality of preset large language models deployed in the electronic device according to the target intent, and then calling the target large language model through the target calling interface, so as to realize the processing of the target demand information by using the target large language model, thereby reducing the cost of the user connecting to the large language model and improving the accuracy of the user's selection of the large language model and the user's usage experience.

[0100] refer to Figure 3 , Figure 3 A flowchart of another information processing method provided in an embodiment of the present application. An information processing method provided in an embodiment of the present application comprises the following steps:

[0101] S301: Obtain target demand information of target users.

[0102] S302: Perform intent recognition on the target demand information to obtain the target intent corresponding to the target user.

[0103] Regarding the above-mentioned step S301 and step S302, step S301 is consistent with the above-mentioned step S101, and step S302 is consistent with the above-mentioned step S102. For details, please refer to the above-mentioned step S101 and step S102, which will not be described in detail in this embodiment.

[0104] S303: Determine a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent.

[0105] S304: Determine the target number of target large language models.

[0106] S305: When the number of targets is at least two, determine a target calling order between the determined target large language models according to the target intent.

[0107] S306: calling each target large language model in sequence according to the target calling order through the target calling interface, so as to process the target demand information by using each target large language model.

[0108] For the above-mentioned steps S303 to S306, in order to realize the processing of more complex target demand information in this embodiment, after determining the target demand information corresponding to the target user according to the target demand information of the target user, the target large language model corresponding to the target intention can be determined from the multiple preset large language models deployed in the electronic device according to the correspondence between the preset different intentions and the preset large language models. After determining the target large language model, the target number of the target large language model can be determined based on all the determined target large language models. When the target number is one, the target large language model can be directly called through the calling interface to process the target demand information using the target large language. When the target number is at least two, the target call order corresponding to the target intention can be determined according to the correspondence between the preset target intention and the calling order between each preset large language model, so that after processing the complex target demand information of the target user, the target call interface can be used to call each of the determined target large language models in turn according to the target call order, and then each target large language model is used to process the target demand information.

[0109] For example, if the target user's target demand information is to convert an audio describing a picture into a picture, in response to the audio-to-picture conversion requirement, the corresponding preset large language model is first selected to convert the audio into text, and then the corresponding preset large language model is selected to convert the text into an image, thereby intelligently connecting the selected preset large language models in series to complete the entire processing flow. The complex task can be processed by calling the target call interface only once, which improves the user experience.

[0110] An information processing method provided by the present embodiment sets a target calling interface for calling different preset large language models in an electronic device in order to enable a user to connect to different preset large language models, so as to determine the target intent corresponding to the target demand information when the target demand information of the target user is obtained, thereby determining a target large language model for processing the target demand information from a plurality of preset large language models deployed in the electronic device according to the target intent, and then calling the target large language model through the target calling interface, so as to realize the processing of the target demand information by using the target large language model, thereby reducing the cost of the user connecting to the large language model and improving the accuracy of the user's selection of the large language model and the user's usage experience.

[0111] refer to Figure 4 , Figure 4 A flowchart of another information processing method provided in an embodiment of the present application. An information processing method provided in an embodiment of the present application comprises the following steps:

[0112] S401: Obtain target demand information of target users.

[0113] S402: Perform intent recognition on the target demand information to obtain the target intent corresponding to the target user.

[0114] Regarding the above-mentioned step S401 and step S402, step S401 is consistent with the above-mentioned step S101, and step S402 is consistent with the above-mentioned step S102. For details, please refer to the above-mentioned step S101 and step S102, which will not be described in detail in this embodiment.

[0115] S403: Obtain target evaluation information corresponding to each preset large language model deployed in the electronic device.

[0116] S404: Determine a second candidate large language model set from a plurality of preset large language models deployed in the electronic device according to the target intent.

[0117] S405: When the second candidate large language model set includes at least two second candidate large language models, determine a second candidate large language model corresponding to the highest target evaluation score from the second candidate large language model set.

[0118] S406: Determine the second candidate large language model corresponding to the highest target evaluation score as the target large language model.

[0119] With respect to the above-mentioned steps S403 to S406, the target evaluation information is used to indicate the target user's evaluation of the processing result obtained by processing the target user's demand information by the preset large language model, and the target evaluation result includes a target evaluation score.

[0120] Among them, after each use of the target large language model to process the target demand information, the processing result of the target large language model processing the target demand information is sent to the target terminal corresponding to the target user, and the processing result corresponding to the target demand information is displayed on the target terminal. After the target terminal displays the processing result corresponding to the target demand information, the target user can evaluate the processing result of the target large language model processing the target demand information based on the target terminal, so that the electronic device receives the target evaluation score corresponding to the target large language model. After obtaining the target large language model, the process of determining the target large language model according to the target intention can be optimized based on the target evaluation score corresponding to the target large language model, so as to improve the overall service quality and user satisfaction. It should be noted that after receiving the target evaluation score corresponding to the target large language model, the corresponding relationship between the target large language model and the target evaluation score can be stored in the electronic device, so as to facilitate subsequent use from the electronic device. The implementation method of determining the second candidate large language model set from multiple preset large language models deployed in the electronic device according to the target intention in step S404 can refer to the above description, and will not be repeated in this embodiment.

[0121] Specifically, after obtaining the target intention corresponding to the target user, in order to determine the target large language model with high target user satisfaction, the target evaluation scores corresponding to each preset large language model deployed in the electronic device are obtained from the electronic device. When at least two second candidate large language models are determined from multiple preset large language models deployed in the electronic device according to the target intention, the second candidate large language model corresponding to the highest target evaluation score among the at least two second candidate large language models is determined as the target large language model. It should be noted that if there are multiple target evaluation scores corresponding to the preset large language model, the multiple target evaluation scores are averaged, and the average is used as the final target evaluation score. In this embodiment, a feedback mechanism is introduced to use the second candidate large language model corresponding to the highest target evaluation score as the target large language model when determining the target large language model, thereby improving the overall service quality and user satisfaction.

[0122] In this embodiment, according to the target intent, a target large language model is determined from a plurality of preset large language models deployed in the electronic device, including:

[0123] Determining a second candidate large language model set from a plurality of preset large language models deployed in the electronic device according to the target intent;

[0124] When the second candidate large language model set includes at least two second candidate large language models, determining a preset fee and a target evaluation score corresponding to each second candidate large language model;

[0125] For each second candidate large language model, determining a first preset weight of a preset fee and a second preset weight of a target evaluation score corresponding to the second candidate large language model;

[0126] Determining a target total score corresponding to the second candidate large language model according to a first preset weight of a preset fee corresponding to the second candidate large language model and a second preset weight of the target evaluation score;

[0127] Determine a second candidate large language model corresponding to the highest target total score from the second candidate large language model set;

[0128] The second candidate large language model corresponding to the highest target total score is determined as the target large language model.

[0129] Among them, the method for determining the preset fee corresponding to the second candidate large language model is consistent with the method for determining the preset fee corresponding to the first candidate large language model. For details, please refer to the above description, which will not be repeated in this embodiment. The first preset weight and the second preset weight can be set according to actual needs. In this embodiment, the specific setting method of the first preset weight and the second preset weight is not limited. After obtaining the first preset weight of the preset fee corresponding to each second candidate large language model and the second preset weight of the target evaluation score, for each second candidate large language model, the weighted sum of the first preset weight, the preset fee, the second preset weight and the target evaluation score is determined, and the weighted sum is used as the target total score. In this embodiment, the target large language model is determined by combining the two indicators of preset fee and target evaluation score, so that the determined target large language model is more in line with the requirements of the target user, thereby improving the overall service quality and user satisfaction.

[0130] S407: calling the target large language model through the target calling interface to process the target demand information using the target large language model.

[0131] In this embodiment, step S407 is consistent with the above-mentioned step S104. For details, please refer to the above-mentioned step S104, which will not be described in detail in this embodiment.

[0132] An information processing method provided by the present embodiment sets a target calling interface for calling different preset large language models in an electronic device in order to enable a user to connect to different preset large language models, so as to determine the target intent corresponding to the target demand information when the target demand information of the target user is obtained, thereby determining a target large language model for processing the target demand information from a plurality of preset large language models deployed in the electronic device according to the target intent, and then calling the target large language model through the target calling interface, so as to realize the processing of the target demand information by using the target large language model, thereby reducing the cost of the user connecting to the large language model and improving the accuracy of the user's selection of the large language model and the user's usage experience.

[0133] refer to Figure 5 , Figure 5 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application. An information processing device provided in an embodiment of the present application is applied to an electronic device, in which a plurality of preset large language models are deployed, and the electronic device has a target calling interface, and the device includes: an acquisition module 10, an identification module 20, a determination module 30 and a processing module 40. The acquisition module 10 is used to acquire the target demand information of the target user, and the target demand information indicates the demand of the target user; the identification module 20 is used to perform intent recognition on the target demand information to obtain the target intent corresponding to the target user; the determination module 30 is used to determine the target large language model from the plurality of preset large language models deployed in the electronic device according to the target intent; the processing module 40 is used to call the target large language model through the target calling interface to process the target demand information using the target large language model.

[0134] In this embodiment, the acquisition module 10 is further used for:

[0135] A balance in a target account corresponding to the target user is obtained, where the target account is pre-created by the target user in the electronic device, and the balance in the target account is used to pay for the preset large language model among the plurality of preset large language models that require paid use.

[0136] In this embodiment, the determination module 30 is further configured to:

[0137] According to the target intent and the balance in the target account, a target large language model is determined from a plurality of the preset large language models deployed in the electronic device.

[0138] In this embodiment, the determination module 30 is further configured to:

[0139] According to the target intent, determining a first candidate large language model set from a plurality of the preset large language models deployed in the electronic device;

[0140] When the first candidate large language model set includes at least two first candidate large language models, determining a preset fee corresponding to each of the first candidate large language models, where the preset fee indicates a fee to be paid for using the first candidate large language model;

[0141] Determine the minimum preset fee from the preset fees corresponding to all the first candidate large language models in the first candidate large language model set;

[0142] When the balance in the target account is greater than or equal to the minimum preset fee, the first candidate large language model corresponding to the minimum preset fee is determined as the target large language model.

[0143] The information processing method provided in this embodiment further includes a push module, which is used to:

[0144] When the balance in the target account is less than the minimum preset fee, generating an alarm prompt message according to the first candidate large language model corresponding to the minimum preset fee;

[0145] The alarm prompt information is pushed to the target terminal where the target user is located.

[0146] In this embodiment, the determination module 30 is further configured to:

[0147] Determining a target number of the target large language models;

[0148] When the number of the targets is at least two, a target calling order between the determined target large language models is determined according to the target intent.

[0149] In this embodiment, the processing module 40 is further used for:

[0150] Each of the target large language models is called in sequence through the target calling interface according to the target calling order, so as to process the target demand information using each of the target large language models.

[0151] In this embodiment, the acquisition module 10 is further used for:

[0152] Obtain target evaluation information corresponding to each of the preset large language models deployed in the electronic device, wherein the target evaluation information is used to indicate the target user's evaluation of the processing result obtained by the preset large language model processing the target user's demand information, and the target evaluation information includes a target evaluation score.

[0153] In this embodiment, the determination module 30 is further configured to:

[0154] Determining a second candidate large language model set from a plurality of the preset large language models deployed in the electronic device according to the target intent;

[0155] When the second candidate large language model set includes at least two second candidate large language models, determining the second candidate large language model corresponding to the highest target evaluation score from the second candidate large language model set;

[0156] The second candidate large language model corresponding to the highest target evaluation score is determined as the target large language model.

[0157] In this embodiment, the acquisition module 10 is further used for:

[0158] In the process of processing the target demand information by using the target large language model, target indicator information corresponding to the target large language model is obtained, and the target indicator information is used to reflect the stability of the target large language model.

[0159] In this embodiment, the determination module 30 is further configured to:

[0160] When it is determined according to the target indicator information that the target large language model is unstable, a backup large language model corresponding to the target large language model is determined.

[0161] In this embodiment, the processing module 40 is further used for:

[0162] The standby large language model is called through the target calling interface to process the target demand information using the standby large language model.

[0163] An information processing device provided by the present embodiment sets a target calling interface for calling different preset large language models in an electronic device in order to enable a user to connect to different preset large language models, so as to determine the target intent corresponding to the target demand information when the target demand information of the target user is obtained, thereby determining a target large language model for processing the target demand information from a plurality of preset large language models deployed in the electronic device according to the target intent, and then calling the target large language model through the target calling interface, so as to realize the processing of the target demand information by using the target large language model, thereby reducing the cost of the user connecting to the large language model and improving the accuracy of the user's selection of the large language model and the user's usage experience.

[0164] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6The electronic device 600 shown includes: at least one processor 601, a memory 602, at least one network interface 604 and other user interfaces 603. The various components in the electronic device 600 are coupled together via a bus system 605. It is understood that the bus system 605 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 605 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 605 is not shown in FIG. Figure 6 Various buses are labeled as bus system 605 .

[0165] The user interface 603 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, a touch pad, or a touch screen).

[0166] It can be understood that the memory 602 in the embodiment of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 602 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0167] In some implementations, the memory 602 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 6021 and an application program 6022 .

[0168] The operating system 6021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 6022 includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. The program for implementing the method of the embodiment of the present application can be included in the application 6022.

[0169] In the embodiment of the present application, by calling the program or instructions stored in the memory 602, specifically, the program or instructions stored in the application 6022, the processor 601 is used to execute the method steps provided by each method embodiment.

[0170] The method disclosed in the above embodiment of the present application can be applied to the processor 601, or implemented by the processor 601. The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 601. The above processor 601 can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software units in the decoding processor can be executed. The software unit can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and completes the steps of the above method in combination with its hardware.

[0171] It is understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPDevice, DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in the present application, or a combination thereof.

[0172] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0173] The electronic device provided in this embodiment may be Figure 6 The electronic device shown in FIG. 1 may perform the following steps: Figure 1 to Figure 4 All steps of the information processing method in Figure 1 to Figure 4 For details on the technical effects of the information processing method shown, please refer to Figure 1 to Figure 4 For the sake of brevity, the relevant description is not repeated here.

[0174] The embodiment of the present application also provides a storage medium (computer-readable storage medium). The storage medium here stores one or more programs. The storage medium may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk or a solid-state drive; the memory may also include a combination of the above-mentioned types of memory.

[0175] When one or more programs in the storage medium can be executed by one or more processors, the above-mentioned information processing method executed on the information processing device side is implemented.

[0176] The processor is used to execute the information processing program stored in the memory to implement the following steps of the information processing method performed on the information processing device side.

[0177] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0178] It should be noted that the phrases "one implementation", "an embodiment", "an exemplary embodiment", "some embodiments", etc. mentioned in the specification indicate that the described embodiments may include certain features, structures or characteristics, but not every embodiment may include the certain features, structures or characteristics. In addition, such phrases do not necessarily refer to the same embodiment. In addition, when describing certain features, structures or characteristics in conjunction with an embodiment, it is within the knowledge of those skilled in the art to implement such features, structures or characteristics in conjunction with other embodiments, whether explicitly or not explicitly described.

[0179] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0180] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An information processing method, characterized in that: Applied to an electronic device, wherein a plurality of preset large language models are deployed in the electronic device, and the electronic device has a target calling interface, the method comprises: Acquire target demand information of a target user, wherein the target demand information indicates the demand of the target user; Performing intent recognition on the target demand information to obtain the target intent corresponding to the target user; According to the target intent, determining a target large language model from a plurality of the preset large language models deployed in the electronic device; The target large language model is called through the target calling interface to process the target demand information using the target large language model.

2. The method according to claim 1, characterized in that Before executing the step of determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent, the method further includes: Acquire a balance in a target account corresponding to the target user, where the target account is pre-created by the target user in the electronic device, and the balance in the target account is used to pay for the fee of the preset large language model among the plurality of preset large language models that require payment for use; The step of determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent includes: According to the target intent and the balance in the target account, a target large language model is determined from a plurality of the preset large language models deployed in the electronic device.

3. The method according to claim 2, characterized in that The step of determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intention and the balance in the target account includes: According to the target intent, determining a first candidate large language model set from a plurality of the preset large language models deployed in the electronic device; When the first candidate large language model set includes at least two first candidate large language models, determining a preset fee corresponding to each of the first candidate large language models, the preset fee indicating a fee required to be paid for using the first candidate large language model; Determine the minimum preset fee from the preset fees corresponding to all the first candidate large language models in the first candidate large language model set; When the balance in the target account is greater than or equal to the minimum preset fee, the first candidate large language model corresponding to the minimum preset fee is determined as the target large language model.

4. The method according to claim 3, characterized in that After executing the step of determining the minimum preset fee from the preset fees corresponding to all the first candidate large language models in the first candidate large language model set, the method further includes: When the balance in the target account is less than the minimum preset fee, generating an alarm prompt message according to the first candidate large language model corresponding to the minimum preset fee; The alarm prompt information is pushed to the target terminal where the target user is located.

5. The method according to claim 1, characterized in that After executing the step of determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent, the method further includes: Determining a target number of the target large language models; When the number of the targets is at least two, determining a target calling order between the determined target large language models according to the target intention; The calling of the target large language model through the target calling interface to process the target demand information using the target large language model includes: Each of the target large language models is called in sequence through the target calling interface according to the target calling order, so as to process the target demand information using each of the target large language models.

6. The method according to claim 1, characterized in that Before executing the step of determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent, the method further includes: Obtaining target evaluation information corresponding to each of the preset large language models deployed in the electronic device, the target evaluation information being used to indicate the target user's evaluation of a processing result obtained by the preset large language model processing the target user's demand information, the target evaluation information including a target evaluation score; The step of determining a target large language model from a plurality of preset large language models deployed in the electronic device according to the target intent includes: Determining a second candidate large language model set from a plurality of the preset large language models deployed in the electronic device according to the target intent; When the second candidate large language model set includes at least two second candidate large language models, determining the second candidate large language model corresponding to the highest target evaluation score from the second candidate large language model set; The second candidate large language model corresponding to the highest target evaluation score is determined as the target large language model.

7. The method according to claim 1, characterized in that The method further comprises: In the process of processing the target demand information by using the target large language model, obtaining target indicator information corresponding to the target large language model, wherein the target indicator information is used to reflect the stability of the target large language model; When it is determined according to the target indicator information that the target large language model is unstable, determining a backup large language model corresponding to the target large language model; The standby large language model is called through the target calling interface to process the target demand information using the standby large language model.

8. An information processing device, characterized in that: Applied to an electronic device, wherein a plurality of preset large language models are deployed in the electronic device, and the electronic device has a target calling interface, and the device comprises: An acquisition module, used to acquire target demand information of a target user, wherein the target demand information indicates the demand of the target user; An identification module, used to perform intent identification on the target demand information to obtain the target intent corresponding to the target user; A determination module, configured to determine a target large language model from a plurality of the preset large language models deployed in the electronic device according to the target intent; A processing module is used to call the target large language model through the target calling interface to process the target demand information using the target large language model.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the processor is used to execute an information processing program stored in the memory to implement the information processing method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the information processing method according to any one of claims 1 to 7.

Images