Intelligent assistant function triggering method and apparatus, electronic device, and storage medium

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for triggering intelligent assistant functions. The method includes: determining a first identifier based on first data; determining a first strategy based on the first identifier and second data; and triggering functions of the intelligent assistant according to the first strategy. This method determines the first identifier using the first data, generates the first strategy based on the first identifier and the second data, and then triggers functions according to the first strategy. This enables intelligent triggering of intelligent assistant functions based on the user's operational behavior, allowing the acquired functions to adapt to the user's needs at different stages, thereby improving the flexibility of the intelligent assistant and enhancing the user experience.

Description

Technical Field

[0001] This invention relates to the field of intelligent assistance technology, and in particular to a method, apparatus, electronic device and storage medium for triggering intelligent assistant functions. Background Technology

[0002] With the widespread application of artificial intelligence technology in content platforms, learning platforms, and tool products, functions such as AI search, AI assistants, and AI summaries are gradually becoming important components of these systems. In existing technologies, these functions are typically invoked through fixed page displays, fixed activation processes, or by user-initiated actions.

[0003] The activation methods of the above-mentioned functions mostly rely on preset rules or manual configuration, lacking a system-level analysis and control mechanism for real-time user behavior characteristics. In practical applications, the following problems may easily occur: On the one hand, users at different stages of use and with different purposes are treated uniformly, and the function intervenes at an inappropriate time, which may interfere with the user's core usage path; on the other hand, when users show behaviors such as ignoring, turning off, or using the function infrequently, the existing solution is difficult to adjust the triggering strategy in a timely manner and continues to display the function in a fixed way, affecting the user experience.

[0004] Furthermore, adjustments to function triggering strategies in existing technologies typically rely on manual intervention or operational configuration, making it difficult to make real-time, adaptive adjustments based on changes in user behavior, resulting in insufficient flexibility and scalability. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for triggering intelligent assistant functions, in order to solve the problem that the triggering of intelligent assistant functions cannot be adjusted in real time according to the operation of the user.

[0006] According to one aspect of the present invention, a method for triggering a smart assistant function is provided, comprising: A first identifier is determined based on the first data; the first data is used to characterize the operation data generated by the operation object performing an operation on the intelligent assistant; the first identifier is used to characterize the processing stage to which the first data belongs; A first strategy is determined based on the first identifier and the second data; the second data is used to characterize the triggering target of the function corresponding to the second scenario in which the intelligent object is located; the first strategy is used to determine the implementation requirements of the functional information. The smart assistant is triggered according to the first strategy.

[0007] According to another aspect of the present invention, a smart assistant function triggering device is provided, comprising: The first identifier determination module is used to determine a first identifier based on first data; the first data is used to characterize the operation data generated by the operation object performing an operation on the intelligent assistant; the first identifier is used to characterize the processing stage to which the first data belongs. The first strategy determination module is used to determine a first strategy based on the first identifier and the second data; the second data is used to characterize the triggering target of the function corresponding to the second scenario in which the intelligent object is located; the first strategy is used to determine the implementation requirements of the functional information. The function triggering module is used to trigger functions of the smart assistant according to the first strategy.

[0008] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to execute the smart assistant function triggering method according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the intelligent assistant function triggering method according to any embodiment of the present invention.

[0010] The technical solution of this invention involves determining a first identifier based on first data. Determining the first identifier provides a suitable time for the intervention of the intelligent assistant, thereby reducing interference from the core usage path of the user and providing a basis for generating a first strategy. Determining the first strategy based on the first identifier and second data makes the intervention of AI functions more aligned with the current usage scenario, improving the auxiliary effect of AI functions. The intelligent assistant is then triggered according to the first strategy. This method determines the first identifier using first data, generates a first strategy based on the first identifier and second data, and triggers functions according to the first strategy. This enables intelligent triggering of the intelligent assistant's functions based on the user's operational behavior, allowing the acquired functions to adapt to the user's needs at different stages, thereby improving the flexibility of the intelligent assistant and enhancing the user experience.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart illustrating a method for triggering a smart assistant function according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a smart assistant function triggering device provided in an embodiment of the present invention; Figure 3 A schematic diagram of the structure of an electronic device for implementing the intelligent assistant function triggering method of this embodiment of the invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Figure 1 This is a flowchart illustrating a method for triggering a smart assistant function according to an embodiment of the present invention. This embodiment is applicable to situations where the function of a smart assistant is intelligently triggered. The method can be executed by a smart assistant function triggering device, which can be implemented in hardware and / or software. This smart assistant function triggering device can be configured in any electronic device with network communication capabilities. Figure 1 As shown, the method includes: S110. Determine a first identifier based on the first data; the first data is used to characterize the operation data generated by the operation object performing an operation on the smart assistant; the first identifier is used to characterize the processing stage to which the first data belongs.

[0017] The first identifier can be one of the following: exploration identifier, usage identifier, or stagnation identifier.

[0018] Specifically, the data in the first set of data is filtered according to preset rules. After filtering, the filtered data is judged according to preset conditions in the preset rules. The state is determined based on the judgment result to obtain the first state. The first state is matched with the corresponding identifier, which is then used as the first identifier.

[0019] Furthermore, the process of acquiring the first data is as follows: the object behavior acquisition module collects the operations performed by the object in the operating system configured with the intelligent assistant to obtain the first data.

[0020] The operating system is a system that enables the operation of objects to complete tasks.

[0021] Furthermore, the object behavior acquisition module is configured in the function dynamic triggering system. The function dynamic triggering system also includes: an operation behavior stage identification module for determining a first identifier based on first data; a first parameter acquisition module for acquiring first parameters; a function triggering decision module for generating a first strategy; and an adjustment module for dynamically adjusting the intelligent assistant that triggers the function.

[0022] Among them, the preset rules include at least: the first preset rule, the second preset rule, and the third preset rule.

[0023] The first preset rule is a rule based on the number of page visits and the dwell time threshold, specifically: the number of page visits is greater than the preset number of visits and / or the dwell time is greater than the preset dwell time threshold.

[0024] The second preset rule is a rule based on operation frequency and the number of repeated operations, specifically: the number of operations is greater than the preset number of operations and / or the number of repeated operations is greater than the preset number of repeated operations.

[0025] The third preset rule is a rule based on the frequency of search or question behavior, specifically: the number of times the search or question behavior occurs is greater than the preset number of occurrences.

[0026] The above steps, including the determination of the first identifier, enable AI functions to intervene at the appropriate stage of operation, reducing interference with the user's core usage path.

[0027] S120. Determine a first strategy based on the first identifier and the second data; the second data is used to characterize the triggering target of the function corresponding to the second scenario in which the intelligent object is located; the first strategy is used to determine the implementation requirements of the function information.

[0028] Specifically, the system matches the corresponding first information based on the first identifier. A first scene is determined based on the current content displayed on the interface. Control parameters are matched from the second data based on the first scene and the first identifier, serving as the first parameter. The first parameter is compared with preset parameters, and the comparison result determines whether the function needs to be triggered, yielding the first result. That is, if the comparison result shows that the first parameter meets the preset parameters, the first result is that the function does not need to be triggered; if the comparison result shows that the first parameter does not meet the preset parameters, the first result is that the function needs to be triggered. If the first result indicates that the function needs to be triggered, the corresponding triggering method is matched based on the first information, and the obtained triggering method and first information are used as the first strategy. If the first result indicates that the function does not need to be triggered, the first strategy is that the smart assistant does not trigger or delays triggering.

[0029] The first piece of information is used to characterize the type of function triggered, which can be one of the following: prompt or guidance type, auxiliary analysis or intelligent summary type, and auxiliary suggestion or location type.

[0030] S130. Trigger the function of the smart assistant according to the first strategy.

[0031] Specifically, the corresponding functions of the intelligent assistant are triggered according to the first strategy, and the triggered functions are displayed on the operating system's display interface for the user's reference.

[0032] Furthermore, after triggering the smart assistant's function according to the first strategy, the interaction information between the user and the smart assistant within a preset time window is obtained, and fourth data is generated based on the obtained interaction information. The fourth data is used to determine whether the smart assistant's function is ignored, whether it is turned off, and the number of function calls, and a second result is generated based on the determination result. The smart assistant's function is then adjusted based on the obtained second result.

[0033] The above steps demonstrate how the generation of the first strategy combines the operational behavior of the target object with the second data to trigger decision-making, making the intervention of AI functions more in line with the needs of the current usage scenario and improving the auxiliary effect of AI functions.

[0034] The process of determining the first identifier based on the first data includes steps A1-A3: Step A1: Determine the first data.

[0035] The first data includes at least: page access path, operation frequency, dwell time, repeated operation behavior, and search or question behavior.

[0036] Specifically, the object behavior acquisition module collects the operations performed by the object in the operating system configured with the intelligent assistant to obtain the first data.

[0037] Furthermore, the collection method is as follows: the object behavior collection module obtains operation information from the pre-configured embedded points, log records, or system event listening units in the operating system.

[0038] Among them, the tracking unit is code embedded in the interactive interface layer of the operation object to obtain operation information. It is used to transform the intangible behavior of the operation object in the operating system front end into quantifiable operation data.

[0039] Among them, the log records are used to actively obtain the operation trajectory of the operation object and store / report this information in a structured manner.

[0040] The system event listening unit is used to listen for system-level behaviors or page state changes triggered during the operation of the operation object on the page through the native API provided by the browser / client, and to execute the specified logic when the event is triggered.

[0041] Step A2: Classify the first data according to preset rules and determine its state to obtain the first state.

[0042] Specifically, the corresponding data in the first data is filtered according to preset rules, and after the filtering is completed, the filtered data is judged according to the preset conditions in the preset rules, and the state is determined according to the judgment result to obtain at least one first state.

[0043] Furthermore, the corresponding data in the first data is filtered according to preset rules as follows: the number of page visits and the current page dwell time in the first data are obtained according to the first preset rule; the number of operations and repeated operations on the current page in the first data are obtained according to the second preset rule; and the number of search or question behaviors in the first data are obtained according to the third preset rule.

[0044] Further, the process for determining at least one first state is as follows: The acquired page visit count and current page dwell time are compared with preset visit count and preset dwell time thresholds, respectively, and the dwell state is determined based on the comparison results. The acquired operation frequency and number of repeated operations are compared with preset operation frequency and preset number of repeated operations, respectively, and the operation state is determined based on the comparison results. The acquired search or question behavior occurrence frequency is compared with a preset occurrence count, and the search state is determined based on the comparison results. The first state is determined based on the acquired dwell state and / or operation state and / or search state.

[0045] Furthermore, the dwell state is determined based on the comparison results as follows: if the number of page visits is greater than or equal to the preset number of visits, or the page dwell time is greater than or equal to the preset duration threshold, then the current dwell state is a long-term dwell state; if the number of page visits is less than the preset number of visits, or the page dwell time is less than the preset duration threshold, then the current dwell state is a short-term dwell state.

[0046] Furthermore, the operation status is determined based on the comparison results as follows: if the operation frequency is greater than or equal to the preset operation frequency, or the number of repeated operations is greater than or equal to the preset number of repeated operations, then the current operation status is a multi-operation status; if the operation frequency is less than the operation frequency, or the number of repeated operations is less than the preset number of repeated operations, then the current operation status is a few-operation status.

[0047] Furthermore, the search status is determined based on the comparison results as follows: if the frequency of search or question behavior is greater than or equal to the preset number of occurrences, the current search status is a multi-search status; if the frequency of search or question behavior is less than the operation frequency, the current search status is a few-search status.

[0048] Furthermore, the first state is determined based on the acquired dwell state and / or operation state and / or search state as follows: If the dwell state is a short-term dwell state, the operation state is a multi-operation state, and the search state is a multi-retrieval state, then the first state is a stagnant state; if the dwell state is a short-term dwell state, the operation state is a multi-operation state, and the search state is a few-retrieval state, then the first state is an exploration state; if the dwell state is a long-term dwell state, the operation state is a few-operation state, and the search state is a few-retrieval state, then the first state is a deep usage stage; if the dwell state is a long-term dwell state, the operation state is a multi-operation state, and the search state is a few-retrieval state, then the first state is a deep usage stage; if the dwell state is a long-term dwell state, the operation state is a multi-operation state, and the search state is a few-retrieval state, then the first state is a deep usage stage. If the dwell time is short, the operation state is low, and the search state is low, then the first state is the exploration state; if the dwell time is short, the operation state is low, and the search state is high, then the first state is the stagnant state; if the dwell time is long, the operation state is low, and the search state is high, then the first state is the deep use state; if the dwell time is long, the operation state is high, and the search state is high, then the first state is the stagnant state.

[0049] In the exploration state, the object being operated on is in a preview and retrieval state for the task to be performed.

[0050] Among them, the deep usage state is when the object being operated on is in a state of deep research on the task to be performed.

[0051] Among them, the stagnant state is when the operation object is in a state of no progress on the current task to be performed.

[0052] Step A3: Match the first state with the corresponding state identifier to obtain the first identifier.

[0053] Specifically, if the first state is the exploration state, the corresponding identifier is the exploration identifier; if the first state is the deep usage state, the corresponding identifier is the usage identifier; if the first state is the stagnant state, the corresponding identifier is the stagnant identifier.

[0054] The determination of the first strategy based on the first identifier and the second data includes steps B1-B3: Step B1: Match the first information according to the first identifier; the first information is used to characterize the type of function triggered.

[0055] Specifically, if the first identifier is an exploration identifier, the corresponding first information is a prompt or guidance type; if the first identifier is a usage identifier, the corresponding first information is an auxiliary analysis or intelligent summary type; if the first identifier is a standstill identifier, the corresponding first information is an auxiliary suggestion or location type.

[0056] Step B2: Determine the first parameter based on the first scenario and the second data; the first scenario is the business scenario category corresponding to the current content displayed on the display interface; the first parameter is used to characterize the control parameters for the next operation of the operation object under the first scenario.

[0057] Specifically, the first scene is determined based on the current content displayed on the display interface, and the corresponding control parameters are matched from the second data based on the first scene and the first identifier, and used as the first parameter.

[0058] Step B3: Generate a first strategy based on the first information and the first parameters.

[0059] Specifically, the first parameter is compared with preset parameters. Based on the comparison result, it is determined whether the function needs to be triggered, resulting in a first result. That is, if the comparison result shows that the first parameter meets the preset parameters, the first result is that the function does not need to be triggered; if the comparison result shows that the first parameter does not meet the preset parameters, the first result is that the function needs to be triggered. If the first result indicates that the function needs to be triggered, the corresponding triggering method is matched according to the first information, and the obtained triggering method and the first information are used as the first strategy. If the first result indicates that the function does not need to be triggered, the first strategy is that the smart assistant does not trigger or delays triggering.

[0060] The generation of the first strategy based on the first information and the first parameters includes steps C1-C2: Step C1: Determine whether the function needs to be triggered based on the first parameter, and obtain the first result.

[0061] Specifically, the first parameter is compared with the preset parameters, and the result determines whether the function needs to be triggered. That is, if the comparison result shows that the first parameter meets the preset parameters, the first result is that the function needs to be triggered; if the comparison result shows that the first parameter does not meet the preset parameters, the first result is that the function does not need to be triggered.

[0062] Further, comparing the first parameter with the preset parameters specifically involves: comparing the priority parameter with the preset priority parameter; if the priority parameter is greater than or equal to the preset priority parameter, the priority parameter meets the requirement; if the priority parameter is less than the preset priority parameter, the priority parameter does not meet the requirement. Comparing the frequency parameter with the preset number of calls; if the frequency parameter is greater than or equal to the preset number of calls, the frequency change meets the requirement; if the frequency parameter is less than the preset number of calls, the frequency change does not meet the requirement. Comparing the experience priority parameter with the preset priority parameter; if the experience priority parameter is greater than or equal to the preset priority parameter, the experience priority meets the requirement; if the experience priority parameter is less than the preset priority parameter, the experience priority does not meet the requirement. If the priority parameter, frequency change, and experience priority all meet the requirements, the first result is that the function needs to be triggered. If any one of them does not meet the requirement, the first result is that the function does not need to be triggered.

[0063] Step C2: Generate a first strategy based on the first result and the first information.

[0064] Specifically, if the first result indicates that the function needs to be triggered, and if the corresponding triggering method is matched according to the first information, the obtained triggering method and the first information will be used as the first strategy. If the first result indicates that the function does not need to be triggered, then the first strategy is for the smart assistant not to trigger or to delay triggering.

[0065] At least one method for obtaining the second data includes steps D1-D3: Step D1: Determine the second scene; the second scene is used to characterize the task scene category to which the content displayed on the display interface at a historical moment belongs.

[0066] Specifically, the task scenario category corresponding to the content displayed on the interface at a historical moment in the operating system is obtained as the second scenario.

[0067] The second scenario can be at least: a learning scenario, a content retrieval scenario, and a tool usage scenario.

[0068] Step D2: Determine the third data; the third data is used to characterize the page type or task flow node displayed on the display interface at a historical moment, and the corresponding action status information.

[0069] Specifically, the page type or task flow node corresponding to the content displayed on the operating system's interface at a historical moment is determined as third-party data.

[0070] Step D3: Determine the second data based on the second scenario and the third data.

[0071] The second data consists of a second scenario and its corresponding control parameters. The control parameters include at least: priority parameters, frequency parameters, and experience priority parameters.

[0072] Among them, the priority parameter is used to characterize the control parameter of the priority of the core operation of the operation object to complete the corresponding task in the second scenario.

[0073] Among them, the frequency parameter is used to characterize the control parameters of the intensity of intervention or the frequency of display of the intelligent assistant in the second scenario.

[0074] Among them, the experience priority parameter is used to characterize the control parameter corresponding to the experience priority of the operation object in the second scenario.

[0075] Specifically, the third data is analyzed and combined with the process nodes of different page types or tasks generated in the second scenario, the control parameters of the intelligent assistant intervention intensity or display frequency, the control parameters of the priority of the operation object to complete the core operation, and the control parameters of the experience priority are used to obtain the second data.

[0076] Furthermore, the second data can also be determined directly based on the second scenario, that is, generated based on the historical operation data of all tasks corresponding to the second scenario.

[0077] Furthermore, the second data can also be determined directly from the third data, that is, the third data is analyzed and the second data is automatically generated based on the analysis results.

[0078] The process of triggering the smart assistant's function according to the first strategy includes steps E1-E3: Step E1: Determine the fourth data; the fourth data is used to characterize the feedback of the operating object after the function is triggered.

[0079] The fourth data includes at least: whether the function is ignored by the target object after it is triggered, whether the function is actively closed by the target object after it is triggered, and the number of times the function is called.

[0080] Specifically, after triggering the smart assistant's function, the interaction information between the user and the smart assistant within a preset time window is obtained, and the fourth data is generated based on the obtained interaction information.

[0081] Step E2: Perform anomaly detection on the fourth data to obtain the second result.

[0082] Specifically, if the function is ignored by the target object after being triggered, the first exception is "function ignored"; if the function is not ignored by the target object after being triggered, the first exception is "function not ignored". If the function is actively closed by the target object after being triggered, the second exception is "function closed"; if the function is not actively closed by the target object after being triggered, the second exception is "function adopted". If the number of function calls is greater than or equal to the preset number of calls, the third exception is "function used normally"; if the number of function calls is less than the preset number of calls, the third exception is "function mismatch". A second result is generated based on the first, second, and third exceptions.

[0083] Furthermore, the second result is generated based on the first, second, and third anomalies as follows: If the first anomaly is that the function is ignored, the second anomaly is that the function is not turned off, and the third anomaly is that the function is inconsistent, then the second result is that the smart assistant is ignored. If the first anomaly is that the function is not ignored, and the second anomaly is that the function is turned off, then the second result is that the smart assistant is turned off. If the first anomaly is that the function is not ignored, the second anomaly is that the function is not turned off, and the third anomaly is that the function is used normally, then the second result is that the smart assistant is used normally. If the first anomaly is that the function is not ignored, the second anomaly is that the function is not turned off, and the third anomaly is that the function is inconsistent, then the second result is that the smart assistant function is inconsistent.

[0084] Step E3: Match the second strategy based on the second result, and adjust the smart assistant according to the second strategy.

[0085] The second strategy could be: reducing the frequency of function triggering, changing the function triggering method, or temporarily disabling function triggering.

[0086] The method for changing the function triggering method can be: active triggering by the operation object, automatic triggering by the operating system, or triggering according to the first strategy.

[0087] Specifically, based on the abnormal state contained in the second result, a corresponding processing strategy is matched, the obtained processing strategy is used to generate a second strategy, and the intelligent assistant is adjusted according to the obtained second strategy.

[0088] Furthermore, the specific handling strategy based on the abnormal state contained in the second result is as follows: If the second result is a function mismatch, the handling strategy is to reduce the function triggering frequency. If the second result is that the smart assistant is ignored, the handling strategy is to temporarily disable function triggering. If the second result is that the smart assistant is disabled, the handling strategy is to change the function triggering method.

[0089] The above steps, by dynamically adjusting the AI ​​function triggering strategy, reduce the cost of manual configuration and intervention, and improve the overall automation level and scalability of the system.

[0090] The process of determining anomalies in the fourth data to obtain the second result includes steps F1-F4: Step F1: Analyze the interaction behavior of the fourth data to obtain the first anomaly.

[0091] Among them, the interaction behavior judgment is used to determine whether the operation object calls the functions provided by the smart assistant based on the fourth data.

[0092] Specifically, interaction data with the operating system is obtained from the fourth data set. This interaction data is then filtered to determine if there is any interaction with the smart assistant, such as clicking on the smart assistant or searching for information using it. Based on the obtained smart assistant interaction data, it is determined whether the functions provided by the smart assistant have been ignored. A first exception is generated based on the result. That is, if no interaction data exists, the function was ignored by the user after being triggered, and the first exception is "function ignored"; if interaction data exists, the function was not ignored by the user after being triggered, and the first exception is "function not ignored".

[0093] Step F2: Perform a function shutdown check on the fourth data to obtain the second exception.

[0094] Specifically, interaction behavior data with the operating system is obtained from the fourth data set, and this data is then filtered to determine if there is any interaction data with the smart assistant. If so, the obtained interaction data is evaluated to see if there is any data indicating that the smart assistant is disabled. If so, a second anomaly is identified, indicating that the function is disabled; otherwise, the second anomaly is identified, indicating that the function is enabled.

[0095] Step F3: Determine the number of function calls based on the fourth data and compare it with the preset number of calls to obtain the third anomaly.

[0096] Specifically, interaction data with the operating system is obtained from the fourth data set. This interaction data is then filtered to determine if there is any interaction data with the smart assistant. If so, the number of times the smart assistant function is invoked is obtained from the acquired interaction data, resulting in the function invocation count. This count is compared with a preset invocation count, and a third anomaly is determined based on the comparison result. That is, if the function invocation count is greater than or equal to the preset invocation count, the third anomaly indicates that the function is being used normally; if the function invocation count is less than the preset invocation count, the third anomaly indicates that the function is not working correctly.

[0097] Step F5: Determine the second result based on the first anomaly, the second anomaly, and the third anomaly.

[0098] Specifically, if the first anomaly is that the function is ignored, the second anomaly is that the function is not turned off, and the third anomaly is that the function is inconsistent, then the second result is that the smart assistant is ignored. If the first anomaly is that the function is not ignored, and the second anomaly is that the function is turned off, then the second result is that the smart assistant is turned off. If the first anomaly is that the function is not ignored, the second anomaly is that the function is not turned off, and the third anomaly is that the function is used normally, then the second result is that the smart assistant is used normally. If the first anomaly is that the function is not ignored, the second anomaly is that the function is not turned off, and the third anomaly is that the function is inconsistent, then the second result is that the smart assistant's function is inconsistent.

[0099] The technical solution of this embodiment determines a first identifier based on first data. Determining the first identifier provides a suitable time for the intervention of the intelligent assistant, thereby reducing interference from the core usage path of the user and providing a basis for generating a first strategy. Determining the first strategy based on the first identifier and second data makes the intervention of AI functions more aligned with the current usage scenario, improving the auxiliary effect of AI functions. The intelligent assistant is then triggered according to the first strategy. This method determines a first identifier based on first data, generates a first strategy based on the first identifier and second data, and triggers functions according to the first strategy. This enables intelligent triggering of intelligent assistant functions based on the user's operational behavior, allowing the acquired functions to adapt to the user's needs at different stages, thereby improving the flexibility of the intelligent assistant and enhancing the user experience.

[0100] Figure 2 This is a schematic diagram of a smart assistant function triggering device provided in an embodiment of the present invention. This embodiment is applicable to situations where the functions of a smart assistant are intelligently triggered. The smart assistant function triggering device can be implemented in hardware and / or software, and can be configured in any electronic device with network communication capabilities. Figure 2 As shown, the device includes: a first identifier determination module 210, a first strategy determination module 220, and a module for determining the intelligent assistant according to a first strategy, wherein: First identifier determination module 210: used to determine a first identifier based on first data; the first data is used to characterize the operation data generated by the operation object performing an operation on the smart assistant; the first identifier is used to characterize the processing stage to which the first data belongs; First strategy determination module 220: used to determine a first strategy based on a first identifier and second data; the second data is used to characterize the triggering target of the function corresponding to the second scenario in which the intelligent object is located; the first strategy is used to determine the implementation requirements of the functional information. Function triggering module 230: used to trigger functions of the smart assistant according to the first strategy.

[0101] Optionally, the first identifier determination module 210 includes: First data determination unit: used to determine the first data; First state determination unit: used to classify the first data according to preset rules and determine the state to obtain the first state; First identifier determination unit: used to match the corresponding state identifier to the first state to obtain the first identifier.

[0102] Optionally, the first strategy determination module 220 includes: First information determination unit: used to match first information according to first identifier; the first information is used to characterize the type of function triggered. First parameter determination unit: used to determine the first parameter based on the first scenario and the second data; the first scenario is the business scenario category corresponding to the current content displayed on the display interface; the first parameter is used to characterize the control parameter of the next operation of the operation object under the first scenario. First strategy determination unit: used to generate a first strategy based on first information and first parameters.

[0103] Optionally, the first strategy determining unit includes: First Result Determination Subunit: Used to determine whether a function needs to be triggered based on the first parameter, and obtain the first result; First strategy determination subunit: used to generate the first strategy based on the first result and the first information.

[0104] Optionally, the first parameter determining unit includes: The second scene determination subunit is used to determine the second scene; the second scene is used to characterize the task scene category to which the content displayed on the display interface at a historical moment belongs. The third data determination subunit is used to determine the third data. The third data is used to characterize the action status information corresponding to the page type or task flow node displayed on the display interface at a historical moment. Second data determination subunit: used to determine the second data based on the second scenario and the third data.

[0105] Optional, the intelligent assistant function triggering device includes: Fourth data determination module: used to determine the fourth data; the fourth data is used to characterize the feedback of the operation object after the function is triggered; Second Result Determination Module: Used to determine the abnormal status of the fourth data and obtain the second result; Adjustment module: Used to match the second strategy based on the second result, and adjust the smart assistant according to the second strategy.

[0106] Optionally, the second result determination module includes: First anomaly determination unit: used to judge the interactive behavior of the fourth data and obtain the first anomaly; Second anomaly determination unit: used to determine the function shutdown of the fourth data and obtain the second anomaly; The third anomaly determination unit is used to determine the number of function calls based on the fourth data and compare it with the preset number of calls to obtain the third anomaly. Second result determination unit: used to determine the second result based on the first anomaly, the second anomaly and the third anomaly.

[0107] The intelligent assistant function triggering device provided in the embodiments of the present invention can execute the intelligent assistant function triggering method provided in any of the embodiments of the present invention, and has the corresponding functions and beneficial effects of executing the intelligent assistant function triggering method. For details, please refer to the relevant operations of the intelligent assistant function triggering method in the foregoing embodiments.

[0108] Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the intelligent assistant function triggering method of this invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0109] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0110] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0111] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as intelligent assistant function triggering methods.

[0112] In some embodiments, the smart assistant function triggering method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the smart assistant function triggering method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the smart assistant function triggering method by any other suitable means (e.g., by means of firmware).

[0113] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0114] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0115] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0116] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0117] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0118] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0119] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0120] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for triggering intelligent assistant functions, characterized in that, include: The first identifier is determined based on the first data; The first data is used to characterize the operation data generated by the operation object performing operations on the smart assistant; The first identifier is used to characterize the processing stage to which the first data belongs; A first strategy is determined based on the first identifier and the second data; The second data is used to characterize the triggering target of the function corresponding to the second scenario in which the intelligent object is located; The first strategy is used to determine the implementation requirements of functional information; The smart assistant is triggered according to the first strategy.

2. The method according to claim 1, characterized in that, Determining the first identifier based on the first data includes: Determine the first data; The first data is classified according to preset rules, and a state determination is performed to obtain the first state; Match the first state with the corresponding state identifier to obtain the first identifier.

3. The method according to claim 1, characterized in that, The step of determining the first strategy based on the first identifier and the second data includes: First information is matched according to a first identifier; the first information is used to characterize the type of function triggered. The first parameter is determined based on the first scenario and the second data; the first scenario is the business scenario category corresponding to the current content displayed on the display interface; the first parameter is used to characterize the control parameters for the next operation of the operation object under the first scenario. A first strategy is generated based on the first information and the first parameters.

4. The method according to claim 3, characterized in that, The step of generating a first strategy based on the first information and the first parameters includes: Based on the first parameter, a judgment is made as to whether the function needs to be triggered, and a first result is obtained; A first strategy is generated based on the first result and the first information.

5. The method according to claim 3, characterized in that, At least one method for obtaining the second data includes: Determine the second scenario; the second scenario is used to characterize the task scenario category to which the content displayed on the display interface at a historical moment belongs. The third data is determined; the third data is used to characterize the action status information corresponding to the page type or task flow node displayed on the display interface at a historical moment. The second data is determined based on the second scenario and the third data.

6. The method according to claim 1, characterized in that, After triggering the function of the smart assistant according to the first strategy, the following is included: Determine the fourth data; the fourth data is used to characterize the feedback of the operating object after the function is triggered; An anomaly assessment is performed on the fourth data to obtain a second result; The second strategy is matched based on the second result, and the smart assistant is adjusted according to the second strategy.

7. The method according to claim 6, characterized in that, The step of performing anomaly detection on the fourth data to obtain a second result includes: The interaction behavior of the fourth data was judged, and the first anomaly was obtained; The function is disabled on the fourth data, resulting in the second anomaly; The number of function calls is determined based on the fourth data and compared with the preset number of calls to obtain the third anomaly; The second result is determined based on the first anomaly, the second anomaly, and the third anomaly.

8. A smart assistant function triggering device, characterized in that, include: The first identifier determination module is used to determine the first identifier based on the first data; The first data is used to characterize the operation data generated by the operation object performing operations on the smart assistant; The first identifier is used to characterize the processing stage to which the first data belongs; The first strategy determination module is used to determine a first strategy based on the first identifier and the second data; the second data is used to characterize the triggering target of the function corresponding to the second scenario in which the intelligent object is located; the first strategy is used to determine the implementation requirements of the functional information. The function triggering module is used to trigger functions of the smart assistant according to the first strategy.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the intelligent assistant function triggering method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the intelligent assistant function triggering method according to any one of claims 1-7.

Images