Task processing method and system for neural network model, storage medium and electronic equipment

Abstract

The invention discloses a task processing method for a neural network model, a storage medium and electronic equipment, and relates to the technical field of smart home, and the task processing method for the neural network model comprises the steps: obtaining a task demand, and selecting a target expert model from a hybrid expert model according to a routing decision mechanism; wherein the task demand comprises input data, and the routing decision mechanism is used for routing an expert model matched with a task corresponding to the task demand from the hybrid expert model; writing the input data into the target expert model for model training to obtain a model output result; and according to the model output result, driving the execution model to output a task execution strategy corresponding to the result. The method can improve the task processing efficiency and response speed. The invention further discloses a task processing system for the neural network model.

Description

Technical Field

[0001] The present application relates to the field of smart home, and specifically, to a task processing method and system, storage medium, and electronic device for a neural network model. Background Art

[0002] At present, with the rapid development of the Internet of Things and artificial intelligence technologies, smart home systems have been rapidly popularized in user home scenarios. Smart home systems mainly include central processors for controlling home appliances, sensors for detecting different types of data, and actuators for executing device commands. However, the current smart home system adopts a single model, which leads to the advantage of smart home systems in processing specific tasks, and the system performance may decline when processing different types or concurrent tasks.

[0003] In order to solve the problem of system performance degradation when processing different types or concurrent tasks, the relevant technology discloses a task processing method for smart homes, including: implementing automation strategies based on cloud computing services or local centralized intelligent control units, and using standard machine learning algorithms for task processing.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] The relevant technology can maintain system performance to a certain extent when processing different types or concurrent tasks. However, when processing tasks, the relevant technology needs to send task-related data to the cloud server for task processing, which makes it impossible for the intelligent control unit to process tasks quickly, resulting in a long response time for task processing, affecting the efficiency of task processing.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] The embodiments of the present disclosure provide a task processing method, system, storage medium and electronic device for a neural network model to improve the efficiency and response speed of task processing.

[0009] In some embodiments, the method includes: obtaining task requirements, selecting a target expert model from a hybrid expert model according to a routing decision mechanism; wherein the task requirements include input data, and the routing decision mechanism is used to route an expert model that is compatible with the task corresponding to the task requirements from the hybrid expert model; writing the input data to the target expert model for model training to obtain a model output result; and according to the model output result, driving the task execution strategy corresponding to the execution model output result.

[0010] In some embodiments, according to the routing decision mechanism, a target expert model is selected from the hybrid expert model, including: extracting semantic data from the input data and determining the semantic complexity; the semantic complexity is determined based on the semantic data and the semantic complexity evaluation function; according to the semantic data and the model application field of each expert model, determining the matching degree between the task requirements and each model application field; weighting the matching degree between the task requirements and each model application field and the semantic complexity to determine the evaluation score of each expert model; selecting the expert model with the highest evaluation score as the target expert model.

[0011] In some embodiments, the degree of match between the task requirements and each model application field is determined based on the semantic data and the model application field of each expert model, including: determining the professional field corresponding to the task requirements based on the semantic data; obtaining the model application field of each expert model, and determining the degree of match between the task requirements and each model application field.

[0012] In some embodiments, according to the routing decision mechanism, a target expert model is selected from the hybrid expert model, including: obtaining the accuracy and average response time of each expert model; determining the performance evaluation score PerScore of each expert model according to the accuracy and average response time of each expert model; obtaining the average load AverLoad of each expert model; and selecting the expert model with the highest PerScore / (AverLoad+1) as the target expert model.

[0013] In some embodiments, the performance evaluation score of each expert model is determined based on the accuracy and average response time of each expert model, including: weighting the accuracy of each expert model and the inverse of the average response time to obtain the performance evaluation score of each expert model.

[0014] In some embodiments, obtaining the average load of each expert model includes: obtaining the current load and historical performance evaluation score of each expert model; and determining the average load of each expert model based on the historical load data and the load quantity.

[0015] In some embodiments, based on the model output result, a task execution strategy corresponding to the model output result is driven to execute, including: determining a target executor and a task execution strategy based on the model output result; and sending a control instruction to the target executor to enable the target executor to execute the task execution strategy.

[0016] In some embodiments, the system includes: a smart home device configured to collect device input data; a router configured to obtain task requirements, select a target expert model from a hybrid expert model according to a routing decision mechanism, and write the input data to the target expert model for model training to obtain a model output result; wherein the task requirements include input data, the input data includes device input data and / or user input data, and the routing decision mechanism is used to route an expert model that is compatible with the task corresponding to the task requirements from the hybrid expert model; a control unit configured to drive a task execution strategy corresponding to the model output result according to the model output result; and an executor configured to execute the task execution strategy corresponding to the model output result.

[0017] In some embodiments, the storage medium, the computer-readable storage medium includes a stored program, wherein the program executes any of the above-described task processing methods for a neural network model when running.

[0018] In some embodiments, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor is configured to execute any of the above-mentioned task processing methods for a neural network model through the computer program.

[0019] The task processing method, system, storage medium and electronic device for a neural network model provided by the embodiments of the present disclosure can achieve the following technical effects:

[0020] The disclosed embodiment can select an expert model suitable for the task corresponding to the task requirement from the hybrid expert model through the local routing decision of the router, use the target expert model to perform model training on the input data to obtain the model output result, and drive the execution of the corresponding task execution strategy through the control unit to make the task execution strategy highly adaptable to the task corresponding to the task requirement. At the same time, the disclosed embodiment does not need to upload the input data contained in the task requirement to the cloud server for processing, and the task can be executed through the cooperation of the router and the control unit. It is conducive to improving the efficiency and response speed of task processing, so that the smart home system has better self-adaptation ability.

[0021] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0023] In order to more clearly illustrate the embodiments of the present application 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.

[0024] Figure 1 is a schematic diagram of a hardware environment for a task processing method for a neural network model according to an embodiment of the present application;

[0025] Figure 2 is a schematic diagram of a task processing method for a neural network model provided by an embodiment of the present disclosure;

[0026] Figure 3 is a schematic diagram of another task processing method for a neural network model provided by an embodiment of the present disclosure;

[0027] Figure 4 is a schematic diagram of another task processing method for a neural network model provided by an embodiment of the present disclosure;

[0028] Figure 5 is a schematic diagram of another task processing method for a neural network model provided by an embodiment of the present disclosure;

[0029] Figure 6 is a schematic diagram of another task processing method for a neural network model provided by an embodiment of the present disclosure;

[0030] Figure 7 is a schematic diagram of a task processing system for a neural network model provided by an embodiment of the present disclosure;

[0031] Figure 8 It is a schematic diagram of another task processing system for a neural network model provided by an embodiment of the present disclosure.

[0032] Reference numerals:

[0033] 102: electronic devices; 104(201): smart home devices; 202: routers;

[0034] 203: control unit; 204: actuator;

[0035] 70: Task processing system for neural network models;

[0036] 700: processor; 701: memory; 702: communication interface; 703: bus. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the solution of the present application, 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 only 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 creative work should fall within the scope of protection of the present application.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] According to one aspect of an embodiment of the present application, a task processing method for a neural network model is provided. The task processing method for a neural network model is widely used in smart home (Smart Home), smart home, smart home device ecology, smart residential (Intelligence House) ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the above-mentioned task processing method for a neural network model can be applied to Figure 1 In the hardware environment composed of the electronic device 102 and the smart home device 104 shown in FIG. Figure 1 As shown, the smart home device 104 is connected to the electronic device 102 via a network.

[0040] The above network may include but is not limited to at least one of the following: wired network, wireless network. The above wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the above wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The electronic device 102 may not be limited to PC, mobile phone, tablet computer. The smart home device 104 may not be limited to smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projection equipment, smart TV, smart clothes drying rack, smart curtain, smart audio and video, smart socket, smart audio, smart speaker, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart sweeping robot, smart window cleaning robot, smart mopping robot, smart air purification equipment, smart steamer, smart microwave oven, smart kitchen treasure, smart purifier, smart water dispenser, smart door lock, etc.

[0041] Combination Figure 2 As shown, the embodiment of the present disclosure provides a task processing method for a neural network model, comprising:

[0042] S01, the router obtains the task requirement and selects the target expert model from the hybrid expert model according to the routing decision mechanism. The task requirement includes input data, and the routing decision mechanism is used to route the expert model that is compatible with the task corresponding to the task requirement from the hybrid expert model.

[0043] In this step, the input data includes user input data sent by the user and / or device input data sent by the smart home device. As an example, the user input data includes voice data or touch data. The device input data includes environmental data or audio data. Among them, the environmental data includes part or all of temperature data, humidity data, wind speed data, and environmental quality data. The environmental data is obtained by detection by different types of sensors. After receiving the task requirements, the router can indirectly obtain the subjective requirements indicated by the user and / or the objective device data transmitted by the device based on the input data contained in the task requirements, so as to accurately obtain the requirements of the task. The hybrid expert model is composed of multiple specialized sub-models (i.e., expert models), and each expert model has good performance in its field of expertise.

[0044] S02, the router writes input data to the target expert model for model training to obtain a model output result. It should be noted that after the router writes input data to the target expert model for model training to obtain a model output result, the router also sends the model output result to the control unit.

[0045] S03, the control unit drives the task execution strategy corresponding to the model output result according to the model output result.

[0046] The task processing method for the neural network model provided by the embodiment of the present disclosure is adopted. After obtaining the task requirements, the embodiment of the present disclosure selects the target expert model from the hybrid expert model according to the routing decision mechanism to determine the expert model suitable for the task corresponding to the task requirements. Then write the input data to the target expert model for model training to obtain the model output result. Finally, the control unit executes the task execution strategy corresponding to the model output result after receiving the model output result. The embodiment of the present disclosure can select the expert model suitable for the task corresponding to the task requirements from the hybrid expert model through the local routing decision of the router, use the target expert model to perform model training on the input data to obtain the model output result, and drive the execution of the corresponding task execution strategy through the control unit so that the task execution strategy is highly adapted to the task corresponding to the task requirements. At the same time, the embodiment of the present disclosure does not need to upload the input data contained in the task requirements to the cloud server for processing, and the execution of the task can be achieved through the cooperation of the router and the control unit. It is conducive to improving the efficiency and response speed of task processing, so that the smart home system has better adaptive capabilities.

[0047] Optionally, combined Figure 3 As shown, the router selects the target expert model from the hybrid expert model according to the routing decision mechanism, including:

[0048] S11, the router extracts semantic data from the input data and determines semantic complexity, wherein the semantic complexity is determined according to the semantic data and a semantic complexity evaluation function.

[0049] In this step, the router determines the semantic complexity in the following manner: the router parses the semantic data to obtain multiple words that construct the semantic data and the frequency of each word and the part of speech of each word in the semantic data; the router inputs each word and the frequency and part of speech of each word into the semantic complexity evaluation function to determine the semantic complexity evaluation value of each word; the router sums the speech complexity evaluation values ​​of all words to obtain the semantic complexity. Among them, the semantic complexity evaluation function is preset, the independent variables of the semantic complexity evaluation function are the frequency of the word and the part of speech of the word, and the dependent variable is the speech complexity evaluation value.

[0050] S12, the router determines the matching degree between the task requirements and each model application field based on the semantic data and the model application field of each expert model.

[0051] In this step, the model application field of the expert model can be obtained by querying the model application field database. The model application field database stores different expert models and the model application fields corresponding to the expert models. As an example, the model application field includes the field of speech recognition, the field of natural language processing, the field of image recognition, the field of environmental perception, or the field of security monitoring.

[0052] S13, the router performs weighted processing on the matching degree and semantic complexity between the task requirements and the application field of each model to determine the evaluation score of each expert model.

[0053] In this step, the router performs weighted processing on the matching degree and semantic complexity between the task requirements and the application field of each model to determine the evaluation score of each expert model, including:

[0054] Score(i)=α×Complexity+β×DMatch(i);

[0055] Where i = 1, 2, ..., N, Score(i), Complexity, DMatch represent the evaluation score, semantic complexity, and matching degree between the task requirements and the model application field of the i-th expert model, α and β represent the first weight coefficient and the second weight coefficient, respectively, and N represents the total number of expert models in the hybrid expert model. α+β=1, 0<α<1 and 0<β<1.

[0056] S14, the router selects the expert model with the highest evaluation score as the target expert model.

[0057] In this step, the router selects the expert model with the highest evaluation score as the target expert model, including: the router sorts the evaluation scores of all expert models, selects the expert model with the highest evaluation score according to the sorting result, and determines it as the target expert model.

[0058] In this way, after receiving the task requirements, the embodiment of the present disclosure first extracts semantic data from the input data and determines the semantic complexity, and then determines the matching degree between the task requirements and each model application field based on the semantic data and the model application field of each expert model. Finally, the semantic complexity and the matching degree between the task requirements and each model application field are weighted to determine the evaluation score of each expert model, and the expert model with the highest evaluation score is selected as the target expert model. In this way, the embodiment of the present disclosure evaluates the expert model score by comprehensively considering the two factors of semantic complexity and the matching degree between the task requirements and each model application field, thereby ensuring the reliability of the evaluation score and facilitating improving the adaptability of the target expert model to the task requirements.

[0059] Optionally, the router determines the matching degree between the task requirement and each model application field according to the semantic data and the model application field of each expert model, including:

[0060] The router determines the professional field corresponding to the task requirements based on the semantic data.

[0061] The router obtains the model application domain of each expert model and determines the matching degree between the task requirements and each model application domain.

[0062] In this way, the embodiment of the present disclosure first determines the professional field corresponding to the task requirement based on the semantic data. Then, the model application field of each expert model is obtained and the matching degree between the patent field of the task requirement and each application field is determined. By determining the above matching degree, it is helpful to obtain an accurate evaluation score, thereby facilitating the selection of a target expert model suitable for the task corresponding to the task requirement.

[0063] Optionally, combined Figure 4 As shown, the router selects the target expert model from the hybrid expert model according to the routing decision mechanism, including:

[0064] S21, the router obtains the accuracy and average response time of each expert model.

[0065] S22, the router determines the performance evaluation score PerScore of each expert model according to the accuracy and average response time of each expert model.

[0066] In this step, the accuracy of the expert model is positively correlated with the performance evaluation score, and the average response time of the expert model is negatively correlated with the performance evaluation score.

[0067] S23, the router obtains the average load AverLoad of each expert model.

[0068] S24, the router selects the expert model with the highest PerScore / (AverLoad+1) as the target expert model.

[0069] In this way, the embodiment of the present disclosure can select the target expert model based on the performance evaluation score and average load of the expert model. The selected target expert model has a relatively low average load and a higher performance evaluation score compared to other expert models, so that the selected target expert model has a shorter response time, which is beneficial to improving the efficiency of task processing.

[0070] Optionally, the router determines a performance evaluation score of each expert model according to the accuracy and average response time of each expert model, including:

[0071] The router performs weighted processing on the accuracy of each expert model and the inverse of the average response time to obtain the performance evaluation score of each expert model.

[0072] In this way, the disclosed embodiment can comprehensively evaluate the performance of the expert model by combining the accuracy and average response time of the historical operation stage of the expert model, thereby improving the accuracy of the expert model performance evaluation score calculation, thereby ensuring that the selection of the target expert model is sufficiently reliable.

[0073] As an example, PerScore = γ × Accuracy + δ × (1 / ResTime);

[0074] Among them, PerScore, Accuracy, and ResTime represent the performance evaluation score, accuracy, and average response time of the expert model, respectively, and γ and δ represent the third weight coefficient and the fourth weight coefficient, respectively.

[0075] γ+δ=1,0<γ<1 and 0<δ<1.

[0076] Optionally, combined Figure 5 As shown, the router obtains the average load AverLoad of each expert model, including:

[0077] S31, the router obtains the current load and historical performance evaluation score of each expert model.

[0078] S32, the router determines the average load AverLoad of each expert model according to the historical load data and the load quantity.

[0079] This is conducive to improving the accuracy of expert model performance evaluation score calculation, thereby ensuring that the selection of the target expert model is sufficiently reliable.

[0080] In this step, Among them, Load j represents the jth load data of the expert model, and m represents the total number of load data of the expert model. Each load data of the expert model can be obtained by regularly collecting historical load data of the expert model. It can be understood that the larger the total number of load data of the expert model, the more reliable the value of the average load.

[0081] Combination Figure 6 As shown, the embodiment of the present disclosure also provides a task processing method for a neural network model, including:

[0082] S41, the router obtains the task requirement and selects the target expert model from the hybrid expert model according to the routing decision mechanism. The task requirement includes input data, and the routing decision mechanism is used to route the expert model that is compatible with the task corresponding to the task requirement from the hybrid expert model.

[0083] S42, the router writes the input data to the target expert model for model training to obtain the model output result.

[0084] S43, the control unit determines the target executor and the task execution strategy according to the model output result.

[0085] S44, the control unit sends a control instruction to the target executor to enable the target executor to execute the task execution strategy.

[0086] The task processing method for a neural network model provided by the embodiment of the present disclosure is adopted. After obtaining the task requirements, the embodiment of the present disclosure selects a target expert model from a hybrid expert model according to a routing decision mechanism to determine an expert model suitable for the task corresponding to the task requirements. Then write the input data to the target expert model for model training to obtain the model output result. Finally, after receiving the model output result, the control unit determines the target executor and the task execution strategy, and sends a control instruction to the target executor to enable the target executor to execute the task execution strategy. The embodiment of the present disclosure can select an expert model suitable for the task corresponding to the task requirements from the hybrid expert model through the local routing decision of the router, use the target expert model to perform model training on the input data to obtain the model output result, and control the target executor to execute the corresponding task execution strategy through the control unit so that the task execution strategy is highly adapted to the task corresponding to the task requirements. At the same time, the embodiment of the present disclosure does not need to upload the input data contained in the task requirements to the cloud server for processing, and the execution of the task can be achieved through the cooperation of the router and the control unit. It is conducive to improving the efficiency and response speed of task processing, so that the smart home system has better adaptive capabilities.

[0087] Combination Figure 7 As shown, the embodiment of the present disclosure provides a task processing system 200 for a neural network model, including a smart home device 201 and a router 202, a control unit 203, and an executor 204. The smart home device 201 is configured to collect device input data. The router 202 is configured to obtain task requirements, select a target expert model from a hybrid expert model according to a routing decision mechanism, and write the input data to the target expert model for model training to obtain a model output result. The routing decision mechanism is used to route an expert model that is adapted to the task corresponding to the task requirement from the hybrid expert model; wherein the task requirement includes input data, and the input data includes device input data and / or user input data. The control unit 203 is configured to drive the task execution strategy corresponding to the model output result according to the model output result. The executor 204 is configured to execute the task execution strategy corresponding to the model output result.

[0088] Using the task processing system 200 for the neural network model provided by the embodiment of the present disclosure, the embodiment of the present disclosure can select an expert model suitable for the task corresponding to the task requirement from the hybrid expert model through the local routing decision of the router, use the target expert model to perform model training on the input data to obtain the model output result, and drive the actuator to execute the corresponding task execution strategy through the control unit to make the task execution strategy highly adapted to the task corresponding to the task requirement. At the same time, the embodiment of the present disclosure does not need to upload the input data contained in the task requirement to the cloud server for processing, and the execution of the task can be achieved through the cooperation of the router, the control unit and the actuator. It is conducive to improving the efficiency and response speed of task processing, so that the smart home system has better self-adaptation ability.

[0089] Combination Figure 8 As shown, the embodiment of the present disclosure provides a task processing system 70 for a neural network model, including a processor (processor) 700 and a memory (memory) 701. Optionally, the device 70 may also include a communication interface (Communication Interface) 702 and a bus 703. Among them, the processor 700, the communication interface 702, and the memory 701 can communicate with each other through the bus 703. The communication interface 702 can be used for information transmission. The processor 700 can call the logic instructions in the memory 701 to execute the task processing method for the neural network model of the above embodiment.

[0090] In addition, the logic instructions in the memory 701 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0091] The memory 701 is a computer-readable storage medium that can be used to store software programs, computer executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor 700 executes the functional application and data processing by running the program instructions / modules stored in the memory 701, that is, the task processing method for the neural network model in the above-mentioned embodiment is implemented.

[0092] The memory 701 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 701 may include a high-speed random access memory and may also include a non-volatile memory.

[0093] The disclosed embodiment provides an electronic device, including: a product body, and the above-mentioned task processing system 70 for the neural network model. The task processing system 70 for the neural network model is installed in the device body. The installation relationship described here is not limited to placement inside the device body, but also includes installation connections with other components of the electronic device, including but not limited to physical connections, electrical connections or signal transmission connections, etc. Those skilled in the art can understand that the task processing system 70 for the neural network model can be adapted to a feasible electronic device body, thereby realizing other feasible embodiments.

[0094] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned task processing method for a neural network model.

[0095] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0096] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0097] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0098] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0099] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment 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 the code, and the module, the program segment or a part of the code 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, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A task processing method for a neural network model, characterized in that: include: Obtaining task requirements, and selecting a target expert model from the hybrid expert model according to a routing decision mechanism; wherein the task requirements include input data, and the routing decision mechanism is used to route an expert model that is adapted to the task corresponding to the task requirements from the hybrid expert model; Write input data to the target expert model for model training and obtain model output results; According to the model output results, the driver executes the task execution strategy corresponding to the model output results.

2. The method according to claim 1, characterized in that According to the routing decision mechanism, a target expert model is selected from the hybrid expert model, including: Extracting semantic data from input data and determining semantic complexity; the semantic complexity is determined based on the semantic data and a semantic complexity evaluation function; According to the semantic data and the model application field of each expert model, determine the matching degree between the task requirements and the application field of each model; The matching degree and semantic complexity between the task requirements and the application field of each model are weighted to determine the evaluation score of each expert model; The expert model with the highest evaluation score is selected as the target expert model.

3. The method according to claim 2, characterized in that According to the semantic data and the model application field of each expert model, determine the matching degree between the task requirements and the application field of each model, including: Determine the professional field corresponding to the task requirements based on semantic data; The model application field of each expert model is obtained, and the matching degree between the task requirements and the application field of each model is determined.

4. The method according to claim 1, characterized in that: According to the routing decision mechanism, a target expert model is selected from the hybrid expert model, including: Obtain the accuracy and average response time of each expert model; According to the accuracy and average response time of each expert model, determine the performance evaluation score PerScore of each expert model; Get the average load AverLoad of each expert model; The expert model with the highest PerScore / (AverLoad+1) is selected as the target expert model.

5. The method according to claim 4, characterized in that According to the accuracy and average response time of each expert model, the performance evaluation score of each expert model is determined, including: The accuracy of each expert model and the inverse of the average response time are weighted to obtain the performance evaluation score of each expert model.

6. The method according to claim 5, characterized in that Get the average load of each expert model, including: Obtain the current load and historical performance evaluation scores of each expert model; Based on the historical load data and the number of loads, the average load of each expert model is determined.

7. The method according to any one of claims 1 to 6, characterized in that: According to the model output results, the driver executes the task execution strategy corresponding to the model output results, including: Determine the target executor and task execution strategy based on the model output results; Send control instructions to the target executor to make the target executor execute the task execution strategy.

8. A task processing system for a neural network model, characterized in that: include: Smart home devices, configured to collect device input data; The router is configured to obtain task requirements, select a target expert model from the hybrid expert model according to a routing decision mechanism, and write input data to the target expert model for model training to obtain a model output result; wherein the task requirements include input data, the input data includes device input data and / or user input data, and the routing decision mechanism is used to route an expert model that is adapted to the task corresponding to the task requirements from the hybrid expert model; A control unit is configured to drive a task execution strategy corresponding to the output result of the execution model according to the output result of the model; The executor is configured to execute the task execution strategy corresponding to the output of the model.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program, when executed, executes the task processing method for a neural network model according to any one of claims 1 to 7.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the task processing method for a neural network model according to any one of claims 1 to 7 through the computer program.

Images