Intelligent response control method and system
By building a target page response model and controlling the target page to perform target operations, the problem of high maintenance costs and poor changes in smart home systems is solved, and efficient management and control of smart devices is realized, which reduces maintenance costs and improves adaptability and scalability.
Patent Information
- Application Number
- CN202411679195.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-22
- Publication Date
- 2025-03-14
AI Technical Summary
In the existing smart home technology, the system maintenance cost is high and the effect of no intrusion changes is poor, making it difficult to achieve efficient management and control of smart devices linkage.
By obtaining IoT data in the target area, a target page response model is built, and according to the target voice and response model, the target page is controlled to perform target operations to respond to voice, including response operations, page call operations, data call operations and intelligent device control operations.
It reduces the maintenance cost during the linkage process of smart devices, realizes sensorless updates, improves the adaptability and scalability of methods, and improves the efficiency and flexibility of page retrieval and smart device control.
Smart Images
Figure CN119626216A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of smart home technology, and in particular to a smart response control method and system. Background Art
[0002] Smart Home mainly refers to the use of computer technology, network communication technology, automatic control technology, etc. to connect various smart devices in the home to achieve intelligent management and control of home facilities. Most of the related technologies use pre-defined rules or scripts to respond to various user needs. The above methods have technical problems such as high system maintenance costs and poor effect of non-sensitive changes.
[0003] Therefore, a new technical solution is urgently needed to solve the above technical problems. Summary of the invention
[0004] According to the embodiments of the present application, an intelligent response control method and system are provided, which can accurately construct a target page response model based on the Internet of Things data of the target area; based on the target voice and the target page response model, the target page can be accurately controlled to perform the target operation to respond to the target voice, which is beneficial to reducing the maintenance cost during the linkage process of smart devices, realizing seamless updates, and improving the adaptability and extensibility of the method.
[0005] In a first aspect of the present application, an intelligent response control method is proposed, comprising:
[0006] Obtain IoT data of the target area;
[0007] Build a target page response model based on IoT data;
[0008] According to the target voice and target page response model, the target page is controlled to perform a target operation to respond to the target voice, wherein the target operation includes: a response operation, a page retrieval operation, a data retrieval operation and / or a smart device control operation.
[0009] In some feasible implementations, the target page response model includes:
[0010] A target intent set corresponding to a target page, a target parameter set corresponding to a target page, a mapping relationship set corresponding to the target intent set and the target parameter set, and a call relationship set between target pages;
[0011] The call relation set includes: a target intention call relation set, and / or a target parameter call relation set.
[0012] In some feasible implementations, each target parameter is independently mapped to a unique target key-value pair set, wherein each target key-value pair belongs to a unique target key-value pair set.
[0013] In some feasible implementations, the target parameter includes: a first target parameter, and / or, a second target parameter;
[0014] The first target parameter is used to control the target page to perform a target response operation to answer the target voice;
[0015] The second target parameter is used to call the target page to perform a target response operation to answer the target voice.
[0016] In some feasible implementations, the first target parameter is used to respond to multiple synonymous control instructions of the target page;
[0017] The second target parameter is used to respond to a variety of call instructions of the target page, wherein the variety of call instructions include: a variety of synonymous call instructions corresponding to the target voice, and / or a preset conditional jump instruction corresponding to the target page.
[0018] In some feasible implementations, the following further includes:
[0019] Determining a target intention set according to a plurality of target voices of a first preset duration;
[0020] Determining a target parameter set based on the target intent set; and / or,
[0021] Determining a target intention set according to the plurality of target voices of a second preset duration;
[0022] According to the target intention set, determine the target parameter set;
[0023] Among them, the first preset time length is shorter than the second preset time length.
[0024] In some feasible implementations, when determining that the target intent set includes: a first intent and a second intent, wherein the first intent corresponds to a first target key-value pair set, the second intent corresponds to a second target key-value pair set, the first target key-value pair set corresponds to a current page, and the second target key-value pair set corresponds to a target calling page;
[0025] The above method further includes:
[0026] Prioritize the current page to perform the first response operation to answer the first intention.
[0027] In some feasible implementations, when it is determined that the target intent set includes: a third intent and a fourth intent, wherein the third intent corresponds to a third target key-value pair set, and the second intent corresponds to a fourth target key-value pair set; the third target key-value pair set corresponds to a first target call page, and the fourth target key-value pair set corresponds to a second target call page,
[0028] The above method further includes:
[0029] Obtaining page code information of the current page, the first target calling page, and the second target calling page;
[0030] Determine, according to the page encoding information, the access path information of the first target access page and the second target access page;
[0031] Determine, according to the call path information, a page call sequence of a first target call page and a second target call page;
[0032] According to the page retrieval sequence, corresponding page retrieval operations are performed to respectively respond to the third intention and the fourth intention.
[0033] In some feasible implementations, the target page is provided with a corresponding target interface for retrieving target data of the target web page and / or controlling the target device to perform a target operation to respond to a target voice.
[0034] In a second aspect of the present application, there is provided an intelligent response control system, comprising:
[0035] An acquisition module is used to acquire IoT data of a target area;
[0036] A construction module is used to build a target page response model based on IoT data;
[0037] The control module controls the target page to perform a target operation to respond to the target voice according to the target voice and the target page response model, wherein the target operation includes: a response operation, a page retrieval operation, a data retrieval operation, and / or a smart device control operation.
[0038] The intelligent response control method and system provided by the embodiment of the present application include: obtaining IoT data of the target area; constructing a target page response model according to the IoT data; controlling the target page to perform a target operation to respond to the target voice according to the target voice and the target page response model, wherein the target operation includes: a response operation, a page retrieval operation, a data retrieval operation, and / or an intelligent device control operation. The present application is conducive to reducing the maintenance cost during the linkage process of intelligent devices, realizing seamless updates, and improving the adaptability and scalability of the present method.
[0039] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:
[0041] Figure 1 A schematic diagram of a process of an intelligent response control method provided in an embodiment of the present application;
[0042] Figure 2 A structural schematic diagram of an intelligent response control system provided in an embodiment of the present application;
[0043] Figure 3 A schematic diagram of the structure of a terminal device or a server suitable for implementing an embodiment of the present application; DETAILED DESCRIPTION
[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.
[0045] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.
[0046] According to a first aspect of an embodiment of the present application, an intelligent response control method is proposed. Figure 1 A schematic diagram of a process of an intelligent response control method 100 provided in an embodiment of the present application is shown as follows: Figure 1 As shown, the method 100 includes:
[0047] Step S110, obtaining IoT data of the target area.
[0048] Exemplarily, the target area may be within a home area or an enterprise area, which is not specifically limited herein.
[0049] In some feasible implementations, the IoT data can be obtained by establishing a connection with an IoT platform in the target area, wherein the type of the connection can include: HTTP connection.
[0050] Step S120: construct a target page response model based on the IoT data.
[0051] Exemplarily, the IoT data may include: call relationship data of smart devices in the target area, smart device operation status data, and user behavior feature data in the target area, etc., to construct the target page response model. It should be noted that each target page in the target page response model can be used to associate with the corresponding smart device.
[0052] Step S130, according to the target voice and the target page response model, control the target page to perform a target operation to respond to the target voice, wherein the target operation includes: a response operation, a page retrieval operation, a data retrieval operation, and / or a smart device control operation.
[0053] Exemplarily, when the user's target intention is determined based on the target voice, the corresponding target page is controlled based on the above-mentioned target page response model to perform corresponding response operations, page jump operations, data retrieval operations, and / or smart device control operations to respond to the above-mentioned target voice and meet the user's target intention.
[0054] Based on this, the intelligent response control method provided by the present application includes: obtaining IoT data of the target area; constructing a target page response model according to the IoT data; and controlling the target page to perform a target operation to respond to the target voice according to the target voice and the target page response model. The present application can realize real-time dynamic adjustment of the target response model according to IoT data, which is beneficial to reducing the maintenance cost in the process of intelligent device linkage, and realizing the seamless update of the target page response model, thereby improving the adaptability and extensibility of the present method. By controlling the target page to perform the corresponding response operation, page retrieval operation, data retrieval operation, and / or intelligent device control operation according to the target voice and the target page response model, it is beneficial to improve the logic of the page retrieval process, the data retrieval process, and / or the intelligent device control process, and improve the flexibility of the target page response mechanism.
[0055] In some feasible implementations, the above-mentioned target page response model includes: a target intent set corresponding to the target page, a target parameter set corresponding to the target page, a mapping relationship set corresponding to the target intent set and the target parameter set, and a calling relationship set between target pages; wherein, the calling relationship set includes: a target intent calling relationship set, and / or a target parameter calling relationship set.
[0056] Exemplarily, the target page can be visually operated based on the web front end through the backend management page, and the target page can be created, edited, and the calling relationship between the target pages can be constructed to achieve the construction of the target intent set corresponding to the target page, the target parameter set corresponding to the target page, the mapping relationship set between the target intent set and the target parameter set, and the calling relationship set between the target pages.
[0057] It should be noted that the above-mentioned target intent set is used to traverse the query to determine whether the user's target intent falls within the service scope of the target page. The target parameter set corresponding to the above-mentioned target page is used to perform corresponding data retrieval operations, and / or smart device control operations. The mapping relationship set corresponding to the above-mentioned target intent set and the target parameter set is used to determine the target parameters that need to be retrieved according to the user's target intent to complete the above-mentioned data retrieval operations, and / or smart device control operations. The retrieval relationship set between the above-mentioned target pages is used to control the transfer from the current page to the target page that matches the user's target intent. The above-mentioned target intent retrieval relationship set is used to perform corresponding page jump operations according to the user's target intent. The above-mentioned target parameter retrieval relationship set is used to perform corresponding page jump operations according to the target parameters.
[0058] Exemplarily, when it is determined that the target intent corresponding to the target voice belongs to the target intent set corresponding to the target page, and the answer can be given without retrieving data or adjusting the smart device, the target page is controlled to directly perform the answer operation.
[0059] Exemplarily, when the target intent set corresponding to the target page is used to determine that the target intent corresponding to the target voice belongs to the above target intent set, but when it is necessary to retrieve data or control an intelligent device, the target parameters corresponding to the target voice are determined according to the mapping relationship set corresponding to the target intent set and the target parameter set, and the data retrieval operation or the intelligent device control operation is performed based on the above target parameters.
[0060] Exemplarily, when it is determined that the target intent corresponding to the target voice does not belong to the target intent set corresponding to the target page, the corresponding page call operation is performed according to the call relationship set between the target pages. It should be noted that, in some feasible implementations, the corresponding page call operation can be performed according to the above-mentioned target intent call relationship set, and / or the above-mentioned page call operation can be performed according to the above-mentioned target parameter call relationship set. After completing the above-mentioned page call operation, the corresponding response operation, data call operation, and / or smart device control operation can be performed by the called page to meet the user's target intent.
[0061] It should be noted that, in some feasible implementations, the target intent set corresponding to the target page, the target parameter set corresponding to the target page, the mapping relationship set corresponding to the target intent set and the target parameter set, and the calling relationship set between the target pages, the data generated by the target page creation process can be encapsulated as a whole and the corresponding process code can be generated to improve the security of this method.
[0062] Based on this, the above method constructs a target intention set corresponding to the target page, a target parameter set corresponding to the target page, a mapping relationship set corresponding to the target intention set and the target parameter set, and a calling relationship set between target pages; wherein the calling relationship set includes: a target intention calling relationship set, and / or a target page response model of a target parameter calling relationship set, which is conducive to improving the construction accuracy of the target page response model, thereby realizing the precise execution of corresponding response operations, page calling operations, data calling operations, and / or smart device control operations according to the user's target intention, thereby improving the response rate of the current page to the user's target intention as well as the calling efficiency of the target page and the response rate to the user's target intention.
[0063] In some feasible implementations, each target parameter is independently mapped to a unique target key-value pair set, wherein each target key-value pair belongs to a unique target key-value pair set.
[0064] Exemplarily, each target parameter corresponds to a unique target key-value pair set, wherein the target key-value pair set includes multiple target key values. It should be noted that the key is a parameter format corresponding to the execution of a page retrieval operation, a data retrieval operation, and / or a smart device control operation process. The value corresponds to all possible sets that can match the key.
[0065] It should be noted that in order to improve the matching efficiency of page retrieval operations, data retrieval operations, and / or smart device control operations, each target key-value pair belongs to a unique target key-value pair set, and there is no overlap between each target key value.
[0066] Exemplarily, after the user completes the target voice input, the target voice may be preprocessed based on the natural language query to generate a target intent set. Specifically, a segmentation or segmentation operation may be performed on the target voice content based on target characters to generate the target intent set. The target characters may include spaces, etc.
[0067] It should be noted that a parameter matching operation can be performed on each target intent in the target intent set to perform corresponding page retrieval operations, data retrieval operations, and / or smart device control operations.
[0068] Based on this, the above method can realize one-to-one precise execution of corresponding page retrieval operations, data retrieval operations, and / or smart device control operations according to the target parameters, which is conducive to improving the control efficiency and control accuracy of page retrieval operations, data retrieval operations and / or smart device control operations.
[0069] In some feasible implementations, the target parameters include: a first target parameter, and / or, a second target parameter; the first target parameter is used to control the target page to perform a target response operation to respond to the target voice; the second target parameter is used to call the target page to perform a target response operation to respond to the target voice.
[0070] Exemplarily, the above-mentioned first target parameter corresponds to a target page control parameter, which is used to control the target page to perform a response operation, a data retrieval operation, and / or a smart device control operation to answer the target voice.
[0071] Exemplarily, the above-mentioned second target parameter corresponds to a global parameter or a session parameter, which is used to perform a page call operation, and control the call target page to perform a response operation, a data call operation, and / or a smart device control operation to respond to the target voice.
[0072] Based on this, the above method divides the target parameters into first target parameters and second target parameters. When it is determined that the target voice input by the user has multiple target intentions, multiple threads can execute corresponding target operations in parallel according to the first target parameter and / or the second target parameter, thereby improving the response speed of the target page response model, improving the efficiency of satisfying the user's target intentions, and thus improving the user experience.
[0073] In some feasible implementations, the first target parameter is used to respond to multiple synonymous control instructions of the target page; the second target parameter is used to respond to multiple call instructions of the target page, wherein the multiple call instructions include: multiple synonymous call instructions corresponding to the target voice and / or preset conditional jump instructions corresponding to the target page.
[0074] Exemplarily, the above-mentioned preset conditions may include: a branch condition for controlling the jump from the current page to the target page.
[0075] Specifically, when the second target parameter meets the preset condition, the control jumps from the current page to the target page corresponding to the preset condition. Each target page can be set with multiple non-intersecting preset conditions to achieve control of jumping from the current page to the target page according to the preset condition.
[0076] Exemplarily, the target key-value pair set may include: bidirectional synonymous control key values. Specifically, the target key-value pair set may include first control direction synonymous key values, such as: enable; enabled; on; open; run; start; turn on; turn up, etc. The target key-value pair set may also include second control direction synonymous key values, such as: close; disable; disabled; down; off; stop; turn down; turn off, etc.
[0077] For example, when the target voice input by the user is "turn on the light", the user's intention is determined to be "on", and the target parameter extracted from the corresponding preset slot is "on". In some feasible implementations, the target parameter can be formatted to improve the recognition efficiency of the target parameter.
[0078] Specifically, when it is determined that the target parameter corresponds to the first target parameter, the light-on operation is performed based on the current page. When it is determined that the target parameter corresponds to the second target parameter, the target page is retrieved and / or jumped to the target page to perform the light-on operation.
[0079] Based on this, the above method can realize the establishment of a unified response mechanism for different language usage characteristics of different users, and improve the recognition and responsiveness of this method to multiple synonymous instructions.
[0080] It should be noted that in the process of determining the target intent set based on multiple target voices, the multiple target voices are used to store and transmit the temporary state or information of the target conversation. Exemplarily, when a user inputs multiple target voices through a speaker device in a smart home device, based on speech-to-text technology (Speech-to-Text, STT), the multiple target voices are recorded to generate historical semantic content, so as to extract corresponding semantic parameters based on the historical semantic content to determine the target intent set. For example: when the historical semantic content input by the user includes: a reservation date, the reservation date can be recorded, and no subsequent questions and answers are generated for the reservation date.
[0081] Exemplarily, the conversation engine can be used to convert and generate target voice content based on multiple target voices, and perform corresponding word segmentation operations to determine the target intent set, wherein the target intent set can be a JSON format data set. The conversation engine can also be used to manage the conversation state, execute the call back process, etc.
[0082] Specifically, the conversation engine can be configured with multiple Agents to serve corresponding fields and execute corresponding response interaction mechanisms. The Agents can be used to serve fields including customer support, order inquiry, and product reservation, etc., which are not specifically limited here.
[0083] It should be noted that each target page can be configured with a corresponding Agent and a corresponding trigger response mechanism to implement corresponding response operations according to the voice input by the user.
[0084] In some feasible implementations, different target pages can be set according to the actual needs of the user to respond to different dialogue stages, for example, a "welcome page", "destination inquiry page", "order confirmation page", etc. can be set. It should be noted that the above dialogue stage is determined in real time according to the conversation content before the moment of waiting for user input.
[0085] In some feasible real-time methods, phrase intent recognition training can be performed in advance on the conversation engine to accurately determine the user's target intent set based on the target speech input by the user. Exemplarily, when the target speech input by the user matches the target phrase, the target intent corresponding to the target phrase is triggered, and the target intent set is generated based on the target intent.
[0086] Exemplarily, when the conversation engine determines that the user's target intention is to inquire about the weather based on the target voice input by the user, the following parameter value can be returned: {"intent":"queryWeather"}; when the conversation engine determines that the user's target intention is to control smart home devices based on the target voice input by the user, the following parameter value can be returned: {"intent":"IoT"}; when the conversation engine determines that the user's target intention is to inquire about news based on the target voice input by the user, the following parameter value can be returned: {"intent":"queryNews"}, so as to control the target page to perform the target operation in response to the target voice.
[0087] Specifically, when the target voice input by the user is "How is the weather today?", a session corresponding to "weather" is created, the target intent is input from the current page, and the parameter value is returned: {"intent":"queryWeather"}. When the above target intent does not meet the target intent set corresponding to the current page, the corresponding parameters are loaded, and the control jumps from the current page to the corresponding target page to implement the corresponding response operation, page retrieval operation, data retrieval operation, and / or smart device control operation based on the target page to respond to the above target voice. It should be noted that when it is determined that the necessary conditions for executing the current response are city parameters and date parameters, the city parameters and date parameters can be determined based on the historical semantic content. When only the date parameter can be extracted based on the historical semantic content, the voice inquiry "Which city do you want to query the weather of" can be continued based on the Agent intelligent body to complete the determination of the necessary parameters, namely the city parameters.
[0088] In some feasible implementations, the above method also includes: determining a target intention set based on multiple target voices of a first preset duration; determining a target parameter set based on the target intention set; and / or determining a target intention set based on multiple target voices of a second preset duration; determining a target parameter set based on the target intention set; wherein the first preset duration is less than the second preset duration.
[0089] Exemplarily, when the matching rate between the multiple target voices of the first preset duration and the target phrase is greater than the preset matching rate, a target intent set is generated based on the multiple target voices of the first preset duration, and a target parameter set is determined based on the target intent set to control the target page to perform the target operation. Among them, the above-mentioned first preset duration and the preset matching rate can be determined according to the user's response accuracy requirements for the target voice. The above-mentioned first preset duration and the preset matching rate are positively correlated with the above-mentioned user's response accuracy requirements for the target voice, that is, the higher the above-mentioned user's response accuracy requirements for the target voice, the longer the first preset duration and the higher the preset matching rate.
[0090] Exemplarily, when the matching rate of the target voices of the first preset duration and the target phrase is less than or equal to the preset matching rate, the target intent set is determined according to the target voices of the second preset duration to control the target page to perform the target operation. The second preset duration and the preset matching rate are positively correlated with the user's response accuracy requirement for the target voice, that is, the higher the user's response accuracy requirement for the target voice, the longer the second preset duration and the higher the preset matching rate.
[0091] It should be noted that, when the target intent set is determined based on multiple target voices of a first preset duration, and when the corresponding target operation performed according to the target intent set does not include a page call operation, after the conversation is completed, a clearing operation is performed on the above-mentioned multiple target voices and the derivative data generated according to the above-mentioned target voices.
[0092] It should be noted that, when determining the target intention set based on multiple target voices of the second preset duration, or performing corresponding target operations based on the target intention set, including: a page call operation, a target storage operation is performed on the above-mentioned multiple target voices and the derivative data generated based on the above-mentioned target voices.
[0093] Based on this, the above method, on the one hand, can realize the accurate determination of the user's target intention set based on multiple target voices, and accurately determine the target parameter set based on the above target intention set, so as to accurately execute the corresponding response operation, page retrieval operation, data retrieval operation, and / or, smart device control operation. On the other hand, the above method can realize the accurate generation of the target intention set based on the multiple target voices corresponding to the first preset time length when the matching rate between the multiple target voices corresponding to the first preset time length and the target phrase is greater than the preset matching rate; and accurately generate the target intention set based on the multiple target voices corresponding to the second preset time length when the matching rate between the multiple target voices corresponding to the first preset time length and the target phrase is less than or equal to the preset matching rate, which is conducive to real-time multi-level regulation of the recognition time of the target intention according to the recognition accuracy of the target voice, thereby improving the response efficiency to the target voice while ensuring the recognition accuracy of the target voice.
[0094] In some feasible implementations, when determining that the target intent set includes: a first intent and a second intent, wherein the first intent corresponds to a first target key-value pair set, the second intent corresponds to a second target key-value pair set, the first target key-value pair set corresponds to the current page, and the second target key-value pair set corresponds to the target calling page; the above method also includes: preferentially controlling the current page to perform a first response operation to respond to the first intent.
[0095] Exemplarily, when it is determined that the target intent set includes multiple target intents, namely the first intent and the second intent, where the first intent belongs to the service scope of the current page and the second intent belongs to the service scope of the target calling page, priority is given to controlling the use of foreground resources to complete the first response operation corresponding to the current page, so as to give priority to responding to the above-mentioned first intent.
[0096] It should be noted that, if the current page does not feedback the corresponding response content within the preset time, the target calling page is called to control the target calling page to perform the second response operation to respond to the second intention, and the current page background is controlled to perform the first response operation to respond to the first operation. After the current page completes the first response operation and / or the target calling page completes the second response operation, the corresponding page is closed.
[0097] It should be noted that, when the current page has fed back the corresponding response content within the preset time, the feedback result of the current page can also be used as an input parameter of the target scheduling page to control the transfer of the target calling page's call operation and the second response operation from the background resource to the foreground resource, thereby improving the fluency and responsiveness of the first response operation. The preset time can be defined by the user according to the urgency of the response, and the preset time is negatively correlated with the urgency of the response, that is, the higher the urgency of the response, the shorter the preset time.
[0098] Based on this, the above method can be implemented. When it is determined that the target intent set includes multiple intents, and the multiple intents include: a first intent belonging to the service scope of the current page and a second intent belonging to the service scope of the target calling page, the current page is preferentially controlled to execute the first response operation to respond to the first intent, which is beneficial to improving the response speed to multiple user intentions and avoiding causing the user to wait for a long time for the response. When the current page has no feedback within a preset time, the target calling page is called, and the target calling page is controlled to execute the second response operation. The current page is controlled to execute the first response operation in the background. When the current page has fed back the corresponding content within the preset time, the target calling page's calling operation and the second response operation are controlled to be transferred from the background resources to the foreground resources. This is beneficial to improving the rationality and scientificity of resource scheduling in the process of multi-task parallel execution in the process of responding to the user's multi-intention instructions, and improving the stability and responsiveness of operation.
[0099] In some feasible embodiments, when determining that the target intent set includes: a third intent and a fourth intent, wherein the third intent corresponds to a third target key-value pair set, and the second intent corresponds to a fourth target key-value pair set; the third target key-value pair set corresponds to a first target calling page, and the fourth target key-value pair set corresponds to a second target calling page, the above method also includes: obtaining page coding information of the current page, the first target calling page, and the second target calling page; determining the calling path information of the first target calling page and the second target calling page according to the page coding information; determining the page calling order of the first target calling page and the second target calling page according to the calling path information; and executing corresponding page calling operations according to the page calling order to respond to the third intent and the fourth intent, respectively.
[0100] It should be noted that each target page is correspondingly provided with unique coding information so as to execute the calling operation and callback operation of the target page.
[0101] Exemplarily, based on the target voice input by the user, it is determined that the user's target intention set includes multiple target intentions, namely the third intention and the fourth intention, wherein the third intention belongs to the service scope of the first target calling page and the fourth intention belongs to the service scope of the second target calling page. The encoding information of the current page, the encoding information of the first target calling page and the encoding information of the second target calling page can be retrieved to determine the calling path information of the first target calling page and the calling path information of the second target calling page. The calling path information of the first target calling page and the calling path information of the second target calling page are compared, and the calling operation of the target calling page with a shorter calling path is preferentially executed to respond to the third intention and the fourth intention.
[0102] Specifically, when it is determined that the calling path of the first target calling page is shorter, the foreground resources are controlled to execute the calling operation of the first target calling page to respond to the third intent, and the background resources are controlled to execute the calling operation of the second target calling page to respond to the fourth intent.
[0103] It should be noted that, if the first target call page does not feedback the corresponding response content within the preset time, the call operation and response operation of the second target call page are changed from being executed by the background resources to being executed by the foreground resources, and the response operation of the first target call page is changed from being executed by the foreground resources to being executed by the background resources. Among them, the above preset time is negatively correlated with the urgency of the response, that is, the higher the urgency of the response, the shorter the preset time.
[0104] It should be noted that when the first target calling page has fed back the corresponding response content within the preset time length, the first target calling page is closed, and the calling operation and response operation of the second target calling page are changed from being executed by background resources to being executed by foreground resources to continue to respond to the fourth intention.
[0105] Based on this, the above method can be implemented, when it is determined that the target intent set contains multiple target intentions that need to be satisfied by performing target operations across pages, the calling paths of the first target calling page and the second target calling page are determined according to the page coding information of the current page, the page coding information of the first target calling page, and the page coding information of the second target calling page, and the foreground resources are preferentially controlled to execute the calling operation of the target calling page with a shorter calling path, and the background resources are controlled to execute the calling operation of the target calling page with a longer calling path, which is conducive to further improving the response efficiency to user needs, and is conducive to further improving the rationality and scientificity of resource scheduling during the parallel execution of multiple cross-page tasks, and improving the stability and responsiveness of operation.
[0106] In some feasible implementations, the target page is provided with a corresponding target interface for retrieving target data of the target web page and / or controlling the target device to perform a target operation to respond to a target voice.
[0107] Exemplarily, the target page may be provided with 0 or 1 target interface. The target interface may be used for data input and / or output at the same time. The input format of the data may include: JSON format.
[0108] Specifically, the above-mentioned target interface can be used to integrate a database, an external API or other system to implement an HTTP-based POST / GET request to request target data from a target web page in response to the above-mentioned target voice, and / or, call a target API to control the smart home device to perform a target operation in response to the target voice.
[0109] Specifically, in the case where the target interface is used to retrieve target data of a target webpage, the calling method of the target interface may include: a web interface calling method.
[0110] Exemplarily, when the target voice input by the user is: "Turn on the lights in the living room", the following parameters can be returned according to the above target voice: {"intent": "IoT"} to enter the smart home parameter initialization page. It should be noted that the smart home parameter initialization page is provided with a target interface for calling and obtaining the relevant list data of the current user's smart home devices, and the actual control page of the smart home devices can be entered. Specifically, the target intent set {target location "living room", target device type "light", target action "turn on"} can be extracted according to the target voice "Turn on the lights in the living room", and the corresponding target parameters can be determined according to the target intent set and the above smart home device related list data, and the target interface can be called according to the above target parameters to respond to the target voice. It should be noted that after completing the above operations, the following content can be fed back based on the current page voice: "OK, I have turned on the lights in the living room for you."
[0111] In some feasible implementations, the target interface may further include: a backend interface for sending target data to a backend server based on an HTTP request to implement dynamic personalized response to the target voice according to the return data of the backend server.
[0112] Exemplarily, when the voice content input by the user is: "How is the weather today?", the following content can be returned based on the target interface: "The weather in Shenzhen today is clear, it is a sunny day."
[0113] Based on this, the above method, by setting a corresponding target interface on the target page to retrieve the target data of the target web page, and / or controlling the target device to perform the target operation to respond to the target voice, can realize network virtual data linkage and / or physical entity operation linkage according to the target interface to realize multi-dimensional response to the target voice, thereby improving the adaptability of the method and enhancing the user experience.
[0114] It should be noted that, in some feasible implementations, the response contents involved in the above method can be fed back to the user based on text-to-speech (TTS) technology.
[0115] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.
[0116] The above is an introduction to the method embodiment. The following is a further explanation of the scheme described in this application through an apparatus embodiment.
[0117] According to a second aspect of the embodiments of the present application, an intelligent response control system is proposed. Figure 2 This is a structural diagram of an intelligent response control system 200 provided in an embodiment of the present application. Figure 2 The system 200 shown includes: an acquisition module 210 , a construction module 220 and a control module 230 .
[0118] An acquisition module 210 is used to acquire IoT data of a target area;
[0119] A construction module 220 is used to construct a target page response model according to the IoT data;
[0120] The control module 230 controls the target page to perform a target operation to respond to the target voice according to the target voice and the target page response model.
[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described method can refer to the corresponding process in the aforementioned system embodiment, and will not be repeated here.
[0122] Figure 3 A schematic diagram of the structure of a terminal device or server suitable for implementing an embodiment of the present application is shown.
[0123] like Figure 3 As shown, the electronic device 300 includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the terminal device or the server are also stored. The CPU 301, the ROM 302 and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.
[0124] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed, so that a computer program read therefrom is installed into the storage section 308 as needed.
[0125] In particular, according to an embodiment of the present application, the above method flow steps can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a machine-readable medium, and the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, the above-mentioned functions defined in the system of the present application are executed.
[0126] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
[0127] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of the code, and the aforementioned module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that 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 boxes represented in succession 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 flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0128] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be arranged in a processor. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves.
[0129] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.
Claims
1. An intelligent response control method, characterized in that: include: Obtain IoT data of the target area; Building a target page response model based on the IoT data; According to the target voice and the target page response model, the target page is controlled to perform a target operation to respond to the target voice, wherein the target operation includes: a response operation, a page retrieval operation, a data retrieval operation and / or a smart device control operation.
2. The method according to claim 1, characterized in that The target page response model includes: A target intent set corresponding to a target page, a target parameter set corresponding to the target page, a mapping relationship set corresponding to the target intent set and the target parameter set, and a call relationship set between target pages; Wherein, the call relation set includes: a target intention call relation set, and / or a target parameter call relation set.
3. The method according to claim 2, characterized in that Each target parameter is independently mapped to a unique set of target key-value pairs, wherein each target key-value pair belongs to a unique set of target key-value pairs.
4. The method according to claim 3, characterized in that The target parameters include: a first target parameter, and / or a second target parameter; The first target parameter is used to control the target page to perform a target response operation to answer the target voice; The second target parameter is used to call the target page to perform a target response operation to answer the target voice.
5. The method according to claim 4, characterized in that The first target parameter is used to respond to multiple synonymous control instructions of the target page; The second target parameter is used to respond to multiple call instructions of the target page, wherein the multiple call instructions include: multiple synonymous call instructions corresponding to the target voice, and / or preset conditional jump instructions corresponding to the target page.
6. The method according to any one of claims 1 to 5, characterized in that Also includes: Determining the target intention set according to the plurality of target voices of the first preset duration; Determining the target parameter set according to the target intention set; and / or, Determining the target intention set according to the plurality of target voices of a second preset duration; Determining the target parameter set according to the target intention set; Among them, the first preset time length is shorter than the second preset time length.
7. The method according to claim 6, characterized in that In the case where it is determined that the target intent set includes: a first intent and a second intent, wherein the first intent corresponds to a first target key-value pair set, the second intent corresponds to a second target key-value pair set, the first target key-value pair set corresponds to a current page, and the second target key-value pair set corresponds to a target calling page; The method further comprises: The current page is preferentially controlled to perform a first response operation to respond to the first intention.
8. The method according to claim 7, characterized in that In the case where it is determined that the target intent set includes: a third intent and a fourth intent, wherein the third intent corresponds to a third target key-value pair set, and the second intent corresponds to a fourth target key-value pair set; the third target key-value pair set corresponds to a first target call page, and the fourth target key-value pair set corresponds to a second target call page; The method further comprises: Obtaining page code information of the current page, the first target calling page, and the second target calling page; Determining, according to the page encoding information, access path information of the first target access page and the second target access page; Determining a page call sequence of the first target call page and the second target call page according to the call path information; According to the page retrieval sequence, corresponding page retrieval operations are performed to respond to the third intention and the fourth intention respectively.
9. The method according to claim 8, characterized in that The target page is provided with a corresponding target interface for retrieving target data of the target web page and / or controlling the target device to perform a target operation to respond to the target voice.
10. An intelligent response control system, characterized in that: include: An acquisition module is used to acquire IoT data of a target area; A construction module, used to construct a target page response model according to the IoT data; The control module controls the target page to perform a target operation to respond to the target voice according to the target voice and the target page response model, wherein the target operation includes: a response operation, a page retrieval operation, a data retrieval operation and / or an intelligent device control operation.