Intelligent scheduling system and method for home decoration scene, electronic equipment and storage medium

Abstract

The invention relates to the field of intelligent scheduling, in particular to an intelligent scheduling system and method for home decoration scenes, electronic equipment and a storage medium. The system comprises an analysis module which analyzes information input by a user based on a large language model to obtain input characteristics; the model selection module is used for determining a target model related to the information input by the user from a plurality of pre-stored models on the basis of the input characteristics obtained by the analysis module; and the processing module is used for processing the information input by the user through the target model to obtain a corresponding processing result.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent scheduling, and more specifically, to a system, method, electronic device and storage medium for intelligent scheduling of home decoration scenes. Background Art

[0002] With the continuous development of artificial intelligence technology, various algorithm models have gradually penetrated into all aspects of people's lives, and the home improvement industry is no exception. Different scenarios and tasks require targeted calls to various detection and segmentation models to meet various detection needs. However, current systems usually lack intelligent scheduling mechanisms, and cannot dynamically judge and call applicable models based on user questions. This makes multi-task processing in home improvement environments inefficient and difficult to achieve true human-computer intelligent interaction. For example, when a user asks a question to inquire about the location or material of a specific object, it is difficult for the system to automatically select an appropriate detection or segmentation model based on the content of the question. This inflexible system limits the user experience and is difficult to adapt to the changing needs of home improvement scenarios. Summary of the invention

[0003] One purpose of the present disclosure is to provide an intelligent scheduling method for home decoration scenarios to solve the problem of intelligent calling of multiple detection models.

[0004] According to a first aspect of the present disclosure, a method for intelligent scheduling of home improvement scenarios is provided, comprising: a parsing module, which parses information input by a user based on a large language model to obtain input features; a model selection module, which determines a target model related to the information input by the user from a plurality of pre-stored models based on the input features obtained by the parsing module; and a processing module, which processes the information input by the user through the target model to obtain a corresponding processing result.

[0005] Optionally, the determining, based on the input features obtained by the parsing module, a target model related to the information input by the user from a plurality of pre-stored models comprises:

[0006] Get the model features of each pre-stored model;

[0007] Determine the similarity between the input feature and each of the pre-stored models, where the similarity is:

[0008]

[0009] Among them, Q i is the input feature, D i is the model feature of the pre-stored model;

[0010] The pre-stored model whose similarity is greater than a first threshold is determined as the target model.

[0011] Optionally, the system further comprises:

[0012] A knowledge base module, wherein the knowledge base module pre-stores knowledge content related to the home improvement scenario;

[0013] a knowledge matching module, wherein the knowledge matching module matches the input feature with the knowledge content to determine the knowledge content related to the information input by the user;

[0014] The processing module also processes the information input by the user based on knowledge content related to the information input by the user to obtain a corresponding processing result.

[0015] Optionally, the matching the input feature with the knowledge content to determine the knowledge content related to the information input by the user includes:

[0016] Obtaining content features corresponding to each of the knowledge contents;

[0017] Determining a matching rate between the input feature and each of the content features;

[0018] The knowledge contents corresponding to the first number of content features with the highest matching rates are determined as the knowledge contents related to the information input by the user.

[0019] Optionally, the processing module further optimizes the processing result through the large language model.

[0020] Optionally, the system further comprises:

[0021] The model adjustment module is used to determine the average response time and the average accuracy of the output results of the target model within a preset time period, and adjust the internal parameters of the target model according to the average response time and the average accuracy to ensure that the average response time and the average accuracy of the output results of the target model after adjustment meet the preset conditions.

[0022] Optionally, the average response time is the ratio of the cumulative sum of the response times of the target model processing the information input by the user within the preset time period to the number of times the target model processes the information input by the user.

[0023] According to a second aspect of the present disclosure, a smart scheduling method for a home decoration scene is provided, comprising:

[0024] Parsing information input by the user according to the large language model to determine input features corresponding to the input information;

[0025] According to the input feature, determining a target model related to the information input by the user from a plurality of pre-stored models;

[0026] The information input by the user is processed through the target model to obtain a corresponding processing result.

[0027] According to a third aspect of the present disclosure, an electronic device is provided, including a processor and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the steps of the method described in the second aspect are implemented.

[0028] According to a fourth aspect of the present disclosure, a storage medium is provided, on which computer instructions are stored, and when the computer instructions are executed by a processor, the steps of the method described in the second aspect are implemented.

[0029] One technical effect of the present disclosure is that it provides an intelligent scheduling system for home decoration scenes, which analyzes the user's input through an analysis module, obtains the input features of the user's input, and determines the target model from multiple pre-stored models based on the input features, and processes the user's input information based on the target model to obtain the processing results required by the user. In this way, the detection model required can be intelligently selected according to the user's input, realizing intelligent human-computer interaction and improving the efficiency and experience of system use.

[0030] Other features and advantages of the embodiments of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the embodiments of the present disclosure.

[0032] Figure 1 is a structural diagram of an intelligent scheduling system for a home decoration scene according to an embodiment;

[0033] Figure 2 is a flow chart of a smart scheduling method for home decoration scenes according to one embodiment;

[0034] Figure 3 is a schematic structural diagram of an electronic device according to an embodiment. DETAILED DESCRIPTION

[0035] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0036] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0037] Techniques and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the techniques and equipment should be considered part of the specification.

[0038] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0039] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0040] The present application embodiment discloses an intelligent scheduling system for home decoration scenes, such as Figure 1 As shown, it includes a parsing module 101, which parses the information input by the user based on the large language model to obtain input features; a model selection module 102, which determines the target model related to the information input by the user from multiple pre-stored models based on the input features obtained by the parsing module; and a processing module 103, which processes the information input by the user through the target model to obtain corresponding processing results.

[0041] In this embodiment, the parsing module may be pre-loaded with a large language model, and the input features of the text information input by the user may be parsed by the large language model. In this example, the large language model first extracts the keywords of the input information, or determines the type of information input by the user. For example, when the user inputs "What is the material of the wall?", the large model parses the keyword "wall material" and identifies the instruction as a detection type question. Afterwards, the features of the keywords or the type of input information are determined as user input features. In this example, the features of the user input may be embodied in the form of feature vectors.

[0042] In this embodiment, the intelligent scheduling system may be provided with a user input module for collecting user input information. A human-computer interaction interface may be provided in the user input module, and the user may input the information he wants to check on the human-computer interaction interface. In addition, the user may also input an image and text information at the same time through the collection module, for example, "query the floor material in the image, etc."

[0043] In one example, multiple models may be pre-stored in the intelligent scheduling system, and these models may be any type of models in the field of home improvement, such as detection models, segmentation models, etc. For example, "human-window distance detection model, wallpaper type determination model, ladder safety detection model, or floor, wall and other material detection model", etc. In this embodiment, after obtaining the input features of the user's input information, the algorithm may be used to analyze the degree of correlation between the features and each model, and one or more models with the highest degree of correlation may be selected as the target model.

[0044] In this embodiment, the system further includes a processing module, which can call multiple pre-stored models to process the information input by the user. For example, when the user inputs "What is the material of the wall?", the processing module can call the pre-stored wall material analysis model to process the target image and obtain the wall material in the target image. Alternatively, when the user inputs "Give me a home decoration design plan, requiring...", the processing module can call the pre-stored plan generation model to directly generate a home decoration design plan that meets its requirements.

[0045] In one example of this embodiment, the intelligent scheduling system includes an image acquisition module, which can collect images or videos of home decoration scenes in real time and store them. When processing the information input by the user, the processing module can call the stored or real-time images and videos. For example, the information input by the user is "Is there anyone smoking at the construction site?", the model selection module determines that the target model is a smoking detection model, and then the processing module processes the image collected by the image acquisition module through the smoking detection model to detect whether there is anyone smoking and obtain the corresponding processing results.

[0046] In this example, an intelligent scheduling system for home decoration scenes is provided. The parsing module parses the user's input, obtains the input features of the user's input, and determines the target model from multiple pre-stored models based on the input features. At the same time, the user's input information is processed based on the target model to obtain the processing results required by the user. In this way, the detection model required can be intelligently selected according to the user's input, realizing intelligent human-computer interaction and improving the efficiency and experience of system use.

[0047] In this embodiment, based on the input features obtained by the parsing module, a target model related to the information input by the user is determined from multiple pre-stored models, including: obtaining the model features of each pre-stored model; determining the similarity between the input features and each of the pre-stored models, and the similarity is:

[0048]

[0049] Among them, Q iis the input feature, D i is the model feature of the pre-stored model; and the pre-stored model whose similarity is greater than a first threshold is determined as the target model.

[0050] In this example, the model feature of each pre-stored model may be a pre-set feature, which may be a text feature of a text description of the function, name or application field corresponding to the model. In one example, the feature may be stored in correspondence with the model in advance, or extracted in real time based on the information of the model through a big data model. In this example, both the input feature and the model feature may contain multiple features, which may be embodied in the form of a feature vector. When determining the similarity between the input feature and the pre-stored model, the cumulative sum of the similarities between each input feature and each model feature may be used as the similarity between the input feature and the pre-stored model.

[0051] In this embodiment, when the similarity between the input feature and the pre-stored model is greater than the threshold, the corresponding pre-stored model can be determined as the target model for calling by the subsequent processing module. In this example, the number of target models can be one or more, that is, if there are multiple pre-stored models whose similarities are greater than the first threshold, these multiple pre-stored models can be set as target models.

[0052] In an example of this embodiment, the system also includes: a knowledge base module, which pre-stores knowledge content related to home improvement scenarios; a knowledge matching module, which matches the knowledge content based on input features to determine the knowledge content related to the information input by the user; and the processing module also processes the information input by the user based on the knowledge content related to the information input by the user to obtain corresponding processing results.

[0053] In this embodiment, the intelligent scheduling system may also include a knowledge base module, which pre-selects and stores knowledge content in related fields. In this example, the information or instructions input by the user may not be processed only according to the pre-stored model. In this example, the knowledge matching module can match the input features corresponding to the input information with each knowledge content in the knowledge base, and determine the knowledge content corresponding to the user input information. After determining the knowledge content related to the input information, the processing module can also answer or process the user input questions based on the relevant knowledge content. In this example, the processing module can process the information or questions input by the user with an auxiliary target model, or process them independently without the target model. For example, when the user raises questions such as material properties or professional terms, the system calls the built-in knowledge base and provides the user with authoritative professional answers in combination with the detection results. The knowledge base brings together rich information on materials, design and decoration. For example, when features such as "texture" and "reflectivity" are detected, the system extracts the knowledge content of corresponding materials such as "solid wood flooring" from the knowledge base. This professional answer effectively makes up for the limitations of the detection model in complex professional knowledge, enabling the system to provide more in-depth feedback in home improvement tasks.

[0054] In an example of the present embodiment, knowledge content related to the information input by the user is determined based on matching input features with knowledge content, including: acquiring content features corresponding to each knowledge content; determining the matching rate between the input features and each content feature; and determining the knowledge content corresponding to the first number of content features with the highest matching rate as the knowledge content related to the information input by the user.

[0055] In this example, the content feature of each knowledge content may be a pre-set feature, which may be a feature corresponding to the text of the knowledge content. In one example, the feature may be stored in correspondence with the knowledge content in advance, or extracted in real time based on the text of the knowledge content through a big data model. In this example, both the input feature and the content feature may contain multiple features, which may be embodied in the form of a feature vector. When determining the matching rate of the input feature and the content feature, the matching rate of each input feature and each content feature may be determined.

[0056] In one example, the matching rate may be represented by the cosine similarity between the vector of the input feature and the vector of the content feature.

[0057] In this example, the specific value of the first quantity can be determined by those skilled in the art according to actual needs. After determining the matching rate between the input feature and each content feature, the matching rates can be arranged from high to low, and the knowledge content corresponding to the first number of content features with the highest matching rate can be determined as content related to the user input information so as to be presented to the user later.

[0058] In this embodiment, the system can also be provided with a knowledge base update module, which can count the number of input features input by the user, and determine which fields the user is more concerned about based on the number of times, so as to update the knowledge base and obtain knowledge content in related fields from the outside by calling other interfaces. For example, when the user inputs "new wall material" many times, the system can automatically obtain more information about the material from the external home improvement database and include it in the knowledge base. This self-learning mechanism ensures that the knowledge base can be dynamically updated during use, gradually expanding the professionalism and practicality of the system.

[0059] In an example of this embodiment, the processing module further optimizes the processing result through a large language model.

[0060] In this example, after obtaining the processing result corresponding to the user input information, the processing module can also optimize the processing result through the large language model, and convert the detection result into a natural language answer that is easy for the user to understand through the large language model. Generate feedback with fluent language and accurate content. For example, for the detection result of "Where is the window?", the system will generate natural language feedback of "The window is in the southeast corner of the room, 1.5 meters from the ground."

[0061] In one example of this embodiment, the system is also provided with a user feedback module, which can receive user feedback on the processing results after the system outputs the optimized processing results. The feedback can be an evaluation of the model's language fluency, content correctness, and user comprehension. This allows targeted adjustments to be made to the large language model or the pre-stored model in the system to improve the content quality and interactive experience of future feedback from the system, and ensure that users can efficiently and intuitively understand the detection results and system recommendations.

[0062] In another example, the processing result output by the system can also be evaluated through a result detection model. The result detection model can be a model such as GPT-Zero to detect whether the processing result output by the system sounds like the language spoken by the user or the language generated by AI.

[0063] In an example of this embodiment, the system also includes: a model adjustment module, which is used to determine the average response time of the target model output results and the average accuracy of the output results within a preset time period, and adjust the internal parameters of the target model according to the average response time and the average accuracy, so that the average response time and the average accuracy of the output results of the target model after adjustment meet the preset conditions.

[0064] In an example of this embodiment, the average response time is the ratio of the cumulative sum of the response time of the target model processing the information input by the user within a preset period to the number of times the target model processes the information input by the user.

[0065] In this embodiment, the model adjustment module can count the accuracy and response time of the output results of a certain target model within a period of time, and calculate the average value of the accuracy and the average value of the response time during this period. In this example, the accuracy of the output result can be directly read from the target model. The average response time can be calculated by the ratio of the sum of the response time and the number of times of each processing of the user input information by the target model during this period. Then, the model parameters of the target model are adjusted based on the average response time and the average accuracy. For example, when the average accuracy is greater than the threshold and meets the preset conditions, but the average response time is too long and does not meet the preset conditions, the internal parameters of the target model can be adjusted so that the model appropriately sacrifices part of the accuracy during the calculation process to speed up the response time, reduce the delay of the user waiting, and improve the user experience. When the average accuracy is less than the threshold and does not meet the preset conditions, but the average response time is less than the threshold and meets the preset conditions, the internal parameters of the target model can be adjusted so that the model appropriately sacrifices part of the response time during the calculation process, processes the user input information more finely, improves the accuracy of the output results, and improves the user experience.

[0066] In an example of this embodiment, a smart scheduling method for home decoration scenes is also provided. Figure 2 As shown, it includes steps S11 to S13.

[0067] S11, parsing the information input by the user according to the large language model, and determining the input features corresponding to the input information;

[0068] S12, determining a target model related to the information input by the user from a plurality of pre-stored models according to the input features;

[0069] S13, processing the information input by the user through the target model to obtain corresponding processing results.

[0070] Optionally, according to the input feature, determining a target model related to the information input by the user from a plurality of pre-stored models, including obtaining a model feature of each pre-stored model;

[0071] Determine the similarity between the input feature and each pre-stored model. The similarity is:

[0072]

[0073] Among them, Q i is the input feature, D i is the model feature of the pre-stored model;

[0074] A pre-stored model with a similarity greater than a first threshold is determined as a target model.

[0075] Optionally, the method also includes: matching the input features with pre-stored knowledge content related to home improvement scenarios to determine knowledge content related to the information input by the user; processing the information input by the user based on the knowledge content related to the information input by the user to obtain corresponding processing results.

[0076] Optionally, based on matching the input features with pre-stored knowledge content related to home improvement scenarios, the knowledge content related to the information input by the user is determined, including: acquiring content features corresponding to each knowledge content; determining a matching rate between the input features and each content feature; and determining the knowledge content corresponding to a first number of content features with the highest matching rate as the knowledge content related to the information input by the user.

[0077] Optionally, after obtaining the corresponding processing result, the method further includes optimizing the processing result by using the large language model.

[0078] Optionally, after obtaining the corresponding processing results, the method also includes: determining the average response time of the target model output results and the average accuracy of the output results within a preset time period, and adjusting the internal parameters of the target model according to the average response time and the average accuracy, so that the average response time and the average accuracy of the output results of the adjusted target model meet preset conditions.

[0079] Optionally, the average response time is the ratio of the cumulative sum of the response times of the target model processing the information input by the user within a preset time period to the number of times the target model processes the information input by the user.

[0080] like Figure 3 As shown, an embodiment of the present application further provides an electronic device 200, including a processor 201 and a memory 202, wherein the memory 202 stores computer instructions, and when the computer instructions are executed by the processor 201, the steps of any method in the embodiment of the intelligent scheduling method for home decoration scenes are implemented.

[0081] The embodiment of the present application also provides a storage medium on which computer instructions are stored. When the computer instructions are executed by a processor, any one of the above-mentioned intelligent scheduling embodiments of the home improvement scene can be implemented, and the same technical effect can be achieved. To avoid repetition, they will not be repeated here.

[0082] Each embodiment in the present disclosure is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and equipment embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0083] The above describes specific embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0084] The embodiments of the present disclosure may be systems, methods and / or computer program products. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the embodiments of the present disclosure.

[0085] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0086] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0087] The computer program instructions for performing the operation of the embodiments of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of a computer-readable program instruction, and the electronic circuit may execute a computer-readable program instruction, thereby realizing various aspects of the embodiments of the present disclosure.

[0088] Various aspects of the embodiments of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0089] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0090] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0091] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of an instruction, and a part of a module, a program segment or an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0092] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An intelligent scheduling system for home decoration scenes, characterized in that: include: A parsing module, wherein the parsing module parses the information input by the user based on the large language model to obtain input features; A model selection module, wherein the model selection module determines a target model related to the information input by the user from a plurality of pre-stored models based on the input features obtained by the parsing module; A processing module processes the information input by the user through the target model to obtain a corresponding processing result.

2. The system according to claim 1, characterized in that The step of determining a target model related to the information input by the user from a plurality of pre-stored models based on the input features obtained by the parsing module comprises: Get the model features of each pre-stored model; Determine the similarity between the input feature and each of the pre-stored models, where the similarity is: Among them, Q i is the input feature, D i is the model feature of the pre-stored model; The pre-stored model whose similarity is greater than a first threshold is determined as the target model.

3. The system according to claim 1, characterized in that The system further comprises: A knowledge base module, wherein the knowledge base module pre-stores knowledge content related to the home improvement scenario; a knowledge matching module, wherein the knowledge matching module matches the input feature with the knowledge content to determine the knowledge content related to the information input by the user; The processing module also processes the information input by the user based on knowledge content related to the information input by the user to obtain a corresponding processing result.

4. The system according to claim 3, characterized in that The matching of the input feature with the knowledge content to determine the knowledge content related to the information input by the user includes: Obtaining content features corresponding to each of the knowledge contents; Determining a matching rate between the input feature and each of the content features; The knowledge contents corresponding to the first number of content features with the highest matching rates are determined as the knowledge contents related to the information input by the user.

5. The system according to claim 4, characterized in that The processing module also optimizes the processing result through the large language model.

6. The system according to claim 1, characterized in that The system further comprises: The model adjustment module is used to determine the average response time and the average accuracy of the output results of the target model within a preset time period, and adjust the internal parameters of the target model according to the average response time and the average accuracy to ensure that the average response time and the average accuracy of the output results of the target model after adjustment meet the preset conditions.

7. The system according to claim 6, characterized in that The average response time is the ratio of the cumulative sum of the response times of the target model processing the information input by the user within the preset time period to the number of times the target model processes the information input by the user.

8. An intelligent scheduling method for home decoration scenes, characterized in that: include: Parsing information input by the user according to the large language model to determine input features corresponding to the input information; According to the input feature, determining a target model related to the information input by the user from a plurality of pre-stored models; The information input by the user is processed through the target model to obtain a corresponding processing result.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the steps of the method according to claim 8 are implemented.

10. A storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed by a processor, the steps of the method according to claim 8 are implemented.

Images