Service system, method, device and storage medium based on prediction model
By analyzing user behavior and using prediction models to predict equipment control instructions, the problem that users need to actively raise demands in the existing technology is solved, and the user experience is automatically provided, which improves the user experience.
Patent Information
- Application Number
- CN202411807090.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-10
- Publication Date
- 2025-04-04
AI Technical Summary
In the prior art, model services require users to actively propose requirements and make accurate inputs, resulting in the user experience being affected.
By analyzing user behavior, predicting device control instructions using prediction models, thereby automatically controlling service equipment to provide services to users.
There is no need for users to actively make demands or make accurate inputs, which improves the user experience and can automatically provide services that meet user needs.
Smart Images
Figure CN119760469A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a service system, method, device and storage medium based on a prediction model. Background Art
[0002] In the related art, with the development of artificial intelligence technology, deep learning models are widely used in various scenarios. Deep learning models can be deployed in a variety of devices, which can be used to perform some tasks.
[0003] However, current model services require users to proactively raise requirements and input questions before they can provide feedback. This working method requires users to take the initiative on the one hand, and requires users to input accurately on the other hand, which seriously affects the user experience. Summary of the invention
[0004] In order to solve or partially solve the problems existing in the related technology, the present application provides a service system, method, device and storage medium based on a prediction model, which can analyze user behavior and use the prediction model to predict device control instructions, so as to control the service equipment to provide services to users by automatically predicting the device control instructions, which is beneficial to improving the user experience by providing users with services that meet their needs.
[0005] In a first aspect, the present application provides a service system based on a prediction model, the system comprising an identification device, a service device, a data storage device and a prediction model; the identification device is used to identify user behavior and trigger a service event when a specified user behavior is identified; the service device is used to respond to device control instructions received from the prediction model and provide services to users according to the device control instructions; the data storage device is used to store target data generated by the service event, and the target data is used to generate input data for the prediction model; the prediction model is used to make predictions based on the input data, output device control instructions corresponding to the input data, and send the device control instructions to the service device.
[0006] In some embodiments, the service device includes a guided service device and / or a non-guided service device; the device control instruction includes a first control instruction for the guided service device and / or a second control instruction for the non-guided service device.
[0007] In some implementations, the guided service device is configured to output a guided prompt according to the first control instruction in response to receiving the first control instruction.
[0008] In some implementations, the non-guided service device is configured to, in response to receiving the second control instruction, execute an operation specified by the second control instruction according to the second control instruction.
[0009] In some embodiments, the target data includes: one or more of data representing user behavior, data representing guiding prompts, and data representing operations specified by the second control instruction; the input data includes one or more of an information sequence representing user behavior, an information sequence representing guiding prompts, and an information sequence representing operations specified by the second control instruction.
[0010] The second aspect of the present application provides a service method based on a prediction model, which is applied to a service system based on a prediction model. The service system based on the prediction model is used to control a service device. The method includes: using an identification device to identify user behavior, and triggering a service event when a specified user behavior is identified; generating data representing the user behavior based on the identified user behavior, and sending the data representing the user behavior to a data storage device; wherein the data storage device is used to store target data generated by the service event, and the target data includes data representing the user behavior; obtaining the target data, and generating input data of a prediction model based on the target data; inputting the input data into the prediction model for prediction, the prediction model outputting a device control instruction corresponding to the input data, and sending the device control instruction to the service device, so that the service device performs the operation specified by the device control instruction.
[0011] In some embodiments, the service device includes: a guided service device and / or a non-guided service device; the device control instructions include: a first control instruction for the guided service device and / or a second control instruction for the non-guided service device; the target data also includes: one or more of data representing guided prompts and data representing operations specified by the second control instructions; the input data includes one or more of an information sequence representing user behavior, an information sequence representing guided prompts, and an information sequence representing operations specified by the second control instructions.
[0012] The third aspect of the present application provides a service device based on a prediction model, which includes: an identification module, which is used to use an identification device to identify user behavior and trigger a service event when a specified user behavior is identified; a first generation module, which is used to generate data representing the user behavior based on the identified user behavior, and send the data representing the user behavior to a data storage device; wherein the data storage device is used to store target data generated by the service event, and the target data includes data representing the user behavior; a second generation module is used to obtain the target data and generate input data of the prediction model based on the target data; a control module is used to input the input data into the prediction model for prediction, the prediction model outputs a device control instruction corresponding to the input data, and sends the device control instruction to the service device, so that the service device performs the operation specified by the device control instruction.
[0013] A fourth aspect of the present application provides an electronic device, including:
[0014] Processor; and
[0015] The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method as described above.
[0016] A fifth aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described above.
[0017] The technical solution provided by the present application may include the following beneficial effects: it is able to analyze user behavior and use a prediction model to predict device control instructions, thereby controlling the service device to provide services to users by automatically predicting the device control instructions, which is beneficial to improving user experience by providing users with services that meet their needs.
[0018] The technical solution of the present application can also: reduce user operations and burdens, such as eliminating the need for users to actively propose requirements and eliminating the need for users to make accurate inputs.
[0019] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail the exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.
[0021] Figure 1 is a schematic diagram of the structure of a service system based on a prediction model shown in an embodiment of the present application;
[0022] Figure 2 It is a flowchart of a service method based on a prediction model shown in an embodiment of the present application;
[0023] Figure 3 is a schematic diagram of a prediction model shown in an embodiment of the present application;
[0024] Figure 4 is a schematic diagram of the structure of a service device based on a prediction model shown in an embodiment of the present application;
[0025] Figure 5 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION
[0026] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.
[0027] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0028] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.
[0029] The current model service requires users to actively propose requirements and input questions before feedback can be given. This working method requires users to take the initiative on the one hand, and requires users to input accurately on the other hand, which seriously affects the user experience.
[0030] In response to the above problems, an embodiment of the present application provides a service system based on a prediction model, which can analyze user behavior and use the prediction model to predict device control instructions, thereby controlling the service equipment to provide services to users by automatically predicting the device control instructions, which is beneficial to improving user experience by providing users with services that meet their needs.
[0031] The technical solution of the embodiments of the present application is described in detail below with reference to the accompanying drawings.
[0032] Figure 1 It is a structural diagram of a service system based on a prediction model shown in an embodiment of the present application.
[0033] See also Figure 1 The prediction model-based service system 100 of this embodiment includes a recognition device 110 , a service device 120 , a data storage device 130 , and a prediction model 140 .
[0034] The identification device 110 is used to identify user behavior and trigger a service event when a specified user behavior is identified.
[0035] The service device 120 is used to provide services to users according to the device control instructions in response to receiving the device control instructions from the prediction model.
[0036] The data storage device 130 is used to store target data generated by service events, and the target data is used to generate input data for the prediction model.
[0037] The prediction model 140 is used to make predictions based on the input data, output device control instructions corresponding to the input data, and send the device control instructions to the service device.
[0038] The service system of the embodiment of the present application can be applied to various scenarios such as vehicle cabins, aircraft cabins, community service stations, hospitals, and homes, and control service equipment to actively provide services to users.
[0039] User behavior may include multiple types of user behaviors that can reflect user needs, such as user's staying behavior, observation behavior, click behavior, purchase behavior, search behavior, behavior representing mood, behavior representing environment temperature, exercise behavior, etc. The user behavior can be recognized by the recognition device 110.
[0040] Specified user behaviors may be stored in advance, such as user staying in a certain area, etc. When the specified user behavior is identified, it reflects that the current user has a certain demand, thereby triggering a service event to control the service device to actively provide services to the user.
[0041] In order to provide a variety of service items, various types of service devices may be configured, such as massage devices, medical devices, music devices, air conditioning devices, gaming devices, etc. The service device 120 may be used to provide relevant services to users in response to receiving device control instructions from the prediction model.
[0042] The data storage device 130 is used to store target data, which may mainly include target data generated by service events, for example, one or more of data representing user behavior, data representing guiding prompts, and data representing operations specified by the second control instruction.
[0043] In some embodiments, since the target data is used to generate input data of the prediction model, the input data may include one or more of an information sequence characterizing user behavior, an information sequence characterizing guided prompts, and an information sequence characterizing operations specified by the second control instruction.
[0044] It is understandable that, in certain cases, services that meet user needs can be provided only by relying on data that characterize user behavior; however, in order to cope with complex situations, or to improve user experience and provide services that better meet user needs, a predictive model is needed to perform continuous predictions in order to provide services that better meet user needs.
[0045] Through each output of the prediction model, multiple types of target data can be obtained; by converting multiple types of target data into input data of the prediction model, the prediction model can be supported to perform continuous prediction.
[0046] The prediction model 140 can analyze and determine the service that the user is most likely to need next. For example, prediction is made based on the input data "data representing user behavior", and the device control instruction "instructing service device A to work" corresponding to the input data "data representing user behavior" is output, and the device control instruction is sent to service device A. For example, after service device A executes the device control instruction, it continues to generate input data "data representing user behavior + data representing the work performed by service device A". Then, the prediction model is also used to make predictions based on the input data "data representing user behavior + data representing the work performed by service device A", and the device control instruction "instructing service device B to work" corresponding to the input data "data representing user behavior + data representing the work performed by service device A" is output, and the device control instruction is sent to service device B until the service event is completed and relevant services are provided to the user.
[0047] The service system based on the prediction model in the embodiment of the present application does not require users to actively propose demands. By analyzing user behavior, the prediction model is used to predict device control instructions, and then the service equipment is controlled to provide services to users by automatically predicting the device control instructions. This is beneficial to improving user experience by providing users with services that meet their needs.
[0048] In some embodiments, the service device includes a guided service device and / or a non-guided service device; the device control instruction includes a first control instruction for the guided service device and / or a second control instruction for the non-guided service device.
[0049] In order to better improve the user experience, the service devices can be divided into guided service devices and non-guided service devices. Among them, the guided service device is used to respond to receiving a first control instruction and output a guided prompt according to the first control instruction. The non-guided service device is used to respond to receiving a second control instruction and perform the operation specified by the second control instruction according to the second control instruction.
[0050] For example, guided service equipment may include AI voice prompt equipment and bank guidance machines. The AI voice prompt equipment issues guided prompt voices to guide users. Non-guided service equipment may provide users with massage services, air conditioning services, music services, etc.
[0051] It can be understood that guided service equipment is helpful for large models to obtain effective input data, accurately predict user needs when making predictions, and provide relevant services to users.
[0052] In order to better understand the present system 100, the content of the present system is further described below in conjunction with embodiments, but the present system is not limited to the following embodiments.
[0053] For example, diagnosis and treatment services are provided in the cabin, and three non-guided service devices are allocated, namely blood pressure device A, fundus laser device B and intraoral repair device C, and one guided service device, namely AI voice prompt device.
[0054] All service information experienced by the user from the moment he enters the cabin will be recorded in an information sequence, which includes user behavior and AI prompts.
[0055] For example, when a user enters the cabin and stops at device A, a service event is triggered. This event can be recorded using an array R with a dimension of t, R(1.x0:A service device stops).
[0056] Then, the prediction model is used to analyze the user behavior, and it is concluded that a voice prompt is needed for the user. The prompt content is text1, and the voice prompt is recorded. The array is R (1.x0: A service device stops; 2.x1: voice prompt text1 for the user).
[0057] Then, the array R is used as input to analyze the user behavior. If it is found that no further reminder is needed, the array R will not be changed.
[0058] If the user continues to go to device C to experience the service trigger event, the array is updated to R (1.x0: A service device stays; 2.x1: voice prompt text1 for the user; 3x2: experience service for C service device).
[0059] Repeat the process and use the new array R as input to continue analyzing user behavior. If it is concluded that a voice prompt is needed for the user, the prompt content is text2, and the voice prompt is recorded. The array is R (1.x0: A service device stays; 2.x1: voice prompt text1 for the user; 3x2: experience service for C service device; 4.x3: voice prompt text2 for the user).
[0060] Repeat this process and continue to use the new array R as input to analyze the user behavior. For example, if it is concluded that the service device C is started for the user, this voice prompt can also be recorded into the array R. The array is R (1.x0: A service device stays; 2.x1: voice prompt text1 for the user; 3x2: experience service for C service device; 4.x3: voice prompt text2 for the user; 5.x4: start service device C for the user).
[0061] Through the embodiment of the present application, when a user enters the vehicle cabin for service, the service that the user is most likely to experience is automatically provided based on the user's behavior. At the same time, the prediction model combines all the user's historical behaviors and the services that have been provided to the user, and predicts the next most likely service after comprehensive analysis. The entire process does not require the user to actively propose their needs to the service system, and all user needs are automatically judged and analyzed by the service system.
[0062] In addition, since there are many types of user behaviors and a wide variety of in-car services, the use of predictive models can easily expand services and provide users with the services they want most every time.
[0063] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides a service method, device, electronic device and corresponding embodiments based on a prediction model.
[0064] Figure 2 This is a flow chart of a service method based on a prediction model shown in an embodiment of the present application.
[0065] See also Figure 2 A service method based on a prediction model is applied to a service system based on a prediction model, and the service system based on a prediction model is used to control a service device. The method includes:
[0066] Step 201: Use an identification device to identify user behavior, and trigger a service event when a specified user behavior is identified.
[0067] Step 202, based on the identified user behavior, generate data representing the user behavior, and send the data representing the user behavior to a data storage device; wherein the data storage device is used to store target data generated by a service event, and the target data includes data representing the user behavior.
[0068] Step 203, obtaining target data, and generating input data of a prediction model according to the target data.
[0069] Step 204: input the input data to the prediction model for prediction. The prediction model outputs a device control instruction corresponding to the input data, and sends the device control instruction to the service device so that the service device executes the operation specified by the device control instruction.
[0070] In some embodiments, the service device includes: a guided service device and / or a non-guided service device; the device control instructions include: a first control instruction for the guided service device and / or a second control instruction for the non-guided service device; the target data also includes: one or more of data representing guided prompts and data representing operations specified by the second control instructions; the input data includes one or more of an information sequence representing user behavior, an information sequence representing guided prompts, and an information sequence representing operations specified by the second control instructions.
[0071] Further explanation of the prediction model is given below. Figure 3 It is a schematic diagram of the prediction model shown in the embodiment of the present application.
[0072] See also Figure 3 , x represents input features, such as information sequence; h represents neural network; z represents output features of each layer of neural network; y represents output features of prediction model, which can be obtained according to output features of each layer of neural network, such as equipment control instructions.
[0073] The input parameters of the prediction model can be {…,x t-1 ,x t ,x t+1 ,…} is used to record user behavior and device services.
[0074] The output parameter can be y t It is the current control command, which may include: AI voice prompt, device control, etc. t Mathematically, an integer parameter.
[0075] W0,W1,W HH and b0,b1,b h is a real number parameter.
[0076] The corresponding hidden layer is {…,h t-1 ,h t ,h t+1 ,…},in m is the number of neurons in the hidden layer, where m can be m=2*t.
[0077] h t =f H (o t )
[0078] in
[0079] o t =W IH x t +W HH h t-1+b h
[0080] f H (·) is the activation function of the hidden layer, b h is the bias vector of the hidden layer. The corresponding output layer is {…,z t-1 ,z t ,z t+1 ,…},
[0081] z t =f O (W HO h t +b o )
[0082] where f O (·) is the activation function of the hidden layer, b o is the bias vector of the hidden layer. We use the hyperbolic tangent function as the activation function:
[0083]
[0084] Finally, we get y t :
[0085] The training process of the prediction model can be the value y calculated by the prediction model t With the actual value y t ′(label), defined as d.
[0086] For example, Δw1 is the error value that needs to be adjusted, w1′ is the adjusted value, and assuming that the learning rate is η, η<1, the calculation result when the error is d is as follows:
[0087]
[0088] w1′=w1+Δw1
[0089] Assume Δw 1h is the error value that needs to be adjusted, w 1h ′ is the adjusted value, the calculation results are as follows:
[0090]
[0091] w 1h ′=w 1h +Δw 1h
[0092] Assume Δw hh is the error value that needs to be adjusted, w hh ′ is the adjusted value, the calculation results are as follows:
[0093]
[0094] w hh ′=w hh +Δw hh
[0095] Assume that Δb1 is the error value that needs to be adjusted, b1′ is the adjusted value, and assume that the learning rate is η, η<1. When the error is d, the calculation result is as follows:
[0096]
[0097] b1′=b1+Δb1
[0098] From then on, a training process is completed and the weight tuning is achieved. The above process is repeated until convergence to adjust the weight value.
[0099] The service method based on the prediction model in the embodiment of the present application does not require the user to actively propose needs. By analyzing the user behavior, the prediction model is used to predict the device control instructions, so as to control the service device to provide services to the user by automatically predicting the device control instructions, which is beneficial to improving the user experience by providing services that meet the user's needs.
[0100] Figure 4 It is a schematic diagram of the structure of a service device based on a prediction model shown in an embodiment of the present application.
[0101] See also Figure 4 The prediction model-based service device 400 of this embodiment includes an identification module 410 , a first generation module 420 , a second generation module 430 and a control module 440 .
[0102] The identification module 410 is used to identify user behavior using an identification device and trigger a service event when a specified user behavior is identified;
[0103] A first generating module 420 is used to generate data representing the user behavior according to the identified user behavior, and send the data representing the user behavior to a data storage device; wherein the data storage device is used to store target data generated by the service event, and the target data includes the data representing the user behavior;
[0104] A second generating module 430 is used to obtain target data and generate input data of a prediction model according to the target data;
[0105] The control module 440 is used to input the input data into the prediction model for prediction. The prediction model outputs a device control instruction corresponding to the input data, and sends the device control instruction to the service device so that the service device performs the operation specified by the device control instruction.
[0106] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated again here.
[0107] According to an embodiment of the present application, any multiple modules in the identification module 410, the first generation module 420, the second generation module 430 and the control module 440 can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the identification module 410, the first generation module 420, the second generation module 430 and the control module 440 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the identification module 410 , the first generation module 420 , the second generation module 430 , and the control module 440 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.
[0108] Figure 5 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application.
[0109] See also Figure 5 , the electronic device 500 includes a memory 510 and a processor 520 .
[0110] The processor 520 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0111] The memory 510 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 520 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, an optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 510 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 510 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.
[0112] The memory 510 stores executable codes, and when the executable codes are processed by the processor 520 , the processor 520 can execute part or all of the methods described above.
[0113] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.
[0114] Alternatively, the present application can also be implemented as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) on which executable code (or computer program or computer instruction code) is stored. When the executable code (or computer program or computer instruction code) is executed by a processor of an electronic device (or server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.
[0115] The embodiments of the present application 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 and spirit 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. A service system based on a prediction model, characterized in that: The system includes an identification device, a service device, a data storage device, and a prediction model; The identification device is used to identify user behavior and trigger a service event when a specified user behavior is identified; The service device is used to respond to receiving the device control instruction from the prediction model and provide a service to the user according to the device control instruction; The data storage device is used to store target data generated by the service event, and the target data is used to generate input data for the prediction model; The prediction model is used to make predictions based on the input data, output device control instructions corresponding to the input data, and send the device control instructions to the service device.
2. The system according to claim 1, characterized in that The service device includes a guided service device and / or a non-guided service device; the device control instruction includes a first control instruction for the guided service device and / or a second control instruction for the non-guided service device.
3. The system according to claim 2, characterized in that The guided service device is configured to output a guided prompt according to the first control instruction in response to receiving the first control instruction.
4. The system according to claim 2, characterized in that The non-guided service device is used to execute the operation specified by the second control instruction according to the second control instruction in response to receiving the second control instruction.
5. The system according to any one of claims 1 to 4, characterized in that: The target data includes: one or more of data representing user behavior, data representing guiding prompts, and data representing operations specified by the second control instruction; the input data includes one or more of an information sequence representing user behavior, an information sequence representing guiding prompts, and an information sequence representing operations specified by the second control instruction.
6. A service method based on a prediction model, characterized in that: The method is applied to a service system based on a prediction model, and the service system based on a prediction model is used to control a service device. The method includes: Use identification devices to identify user behavior and trigger service events when specified user behavior is identified; Generate data representing the user behavior according to the identified user behavior, and send the data representing the user behavior to a data storage device; wherein the data storage device is used to store target data generated by the service event, and the target data includes the data representing the user behavior; Acquire the target data, and generate input data of a prediction model according to the target data; The input data is input into a prediction model for prediction, the prediction model outputs a device control instruction corresponding to the input data, and the device control instruction is sent to a service device so that the service device executes an operation specified by the device control instruction.
7. The method according to claim 6, characterized in that The service device includes: a guided service device and / or a non-guided service device; the device control instructions include: a first control instruction for the guided service device and / or a second control instruction for the non-guided service device; the target data also includes: one or more of data representing guided prompts and data representing operations specified by the second control instructions; the input data includes one or more of an information sequence representing user behavior, an information sequence representing guided prompts, and an information sequence representing operations specified by the second control instructions.
8. A service device based on a prediction model, characterized in that: The device comprises: An identification module, used to identify user behavior using an identification device and trigger a service event when a specified user behavior is identified; A first generating module is used to generate data representing the user behavior according to the identified user behavior, and send the data representing the user behavior to a data storage device; wherein the data storage device is used to store target data generated by the service event, and the target data includes the data representing the user behavior; A second generating module is used to obtain the target data and generate input data of a prediction model according to the target data; The control module is used to input the input data into the prediction model for prediction, the prediction model outputs a device control instruction corresponding to the input data, and sends the device control instruction to the service device so that the service device performs the operation specified by the device control instruction.
9. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to claim 6 or 7.
10. A computer-readable storage medium having executable codes stored thereon, which, when executed by a processor of an electronic device, causes the processor to execute the method according to claim 6 or 7.