A mouse-based data processing method and system

Abstract

The application provides a mouse-based data processing method and system, and belongs to the technical field of data processing, and specifically comprises the following steps: based on a jump processing strategy, different mouse jump control processing under an intelligent key is performed, and based on mouse operation data after the jump processing, determination of suspected abnormal jump data of the mouse is performed; based on the suspected abnormal jump data, when optimization and adjustment processing of the jump processing strategy is required, a recognition deviation process in the mouse under different voice content is determined; based on the jump processing strategy of different mice and the recognition deviation process of the mouse using the basic jump strategy, a recognition update method of the optimization processing target of the jump processing strategy in the mouse is determined, and the matching degree of the jump and the user demand is ensured.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, and in particular relates to a data processing method and system based on a mouse. Background Technology

[0002] Traditional stock market investors typically go through multiple cumbersome steps when monitoring and trading, such as "switching windows - searching for stocks - opening the interface - entering the code." Especially in rapidly fluctuating market conditions, the mouse is merely a pointing tool and cannot actively filter or extract key data (such as abnormal price movements or capital inflows), nor can it directly locate the stocks the user is most concerned about in their holdings or watchlist, resulting in operational delays and the risk of missing buy and sell points.

[0003] Existing technical solutions have enabled some mice to have data processing functions. For example, in invention patent application CN103049102B, "Mouse Data Processing Device and Mouse Data Processing Method," the displacement of the mouse is calculated based on the acceleration, multiplier, and movement time of the mouse. The movement path of the mouse is determined according to the starting point of the movement and the displacement. Therefore, using the smart buttons of the mouse and the voice recognition results, jump processing can be easily performed, greatly improving the efficiency of positioning processing. However, the following technical problems exist: In the process of speech recognition processing, there may be deviations in speech recognition, which may lead to the jump results being difficult to match with the user's needs. Therefore, how to determine the mouse jump processing method based on the reliability of the mouse's speech recognition processing, and how to optimize and adjust different mouse jump processing strategies based on suspected abnormal jump data, so as to ensure the efficiency of training data acquisition and processing and the reliability of jump processing, has become an urgent technical problem to be solved.

[0004] Therefore, there is an urgent need for a mouse-based data processing method and system. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides a mouse-based data processing method, which includes: S1 determines the mouse's voice recognition strategy based on the association between the mouse's smart buttons and the target software's software modules, as well as the usage data of the smart buttons. It then determines the smart button's jump processing strategy based on the voice recognition strategies of different mice and the recognition data under different voice content. S2 performs different mouse jump control processing under smart buttons based on the jump processing strategy, and determines the suspected abnormal jump data of the mouse based on the mouse operation data after jump processing. When it is determined that the jump processing strategy needs to be optimized and adjusted based on the suspected abnormal jump data, proceed to the next step. S3 determines the recognition deviation process in the mouse based on recognition data under different speech content, and determines the recognition update method of the optimized processing target of the jump processing strategy in the mouse based on different mouse jump processing strategies and the recognition deviation process of the mouse using the basic jump strategy.

[0006] The beneficial effects of this invention are as follows: Based on the speech recognition strategies of different mice and the degree of recognition consistency under different speech content, the recognition deviation risk of the mouse under different speech content is determined. The worse the recognition consistency, the fewer mice that perform speech recognition processing regardless of whether the mouse is turned on, and the higher the recognition deviation risk. The recognition deviation risk is used to determine the jump processing strategy, which avoids unnecessary jump processing and also ensures that the jump processing is linked to user needs.

[0007] Based on the proportion of mice using the basic jump strategy and the recognition deviation process of mice with different available recognition targets, the timeliness of updating training data using mice with the basic jump strategy is determined. The higher the proportion of mice using the basic jump strategy and the greater the recognition deviation process of mice with different available recognition targets, the higher the timeliness of updating training data. The timeliness of updating training data is then used to optimize the jump processing strategy in mice and determine the target recognition update method, laying the foundation for achieving a balanced control of the reliability of jump processing and the reliability of updating training data.

[0008] Furthermore, the association between the smart button and the target software module is determined based on the activation strategy of the target software module corresponding to the voice recognition result of the mouse when the smart button is activated.

[0009] Furthermore, the usage data of the smart button includes the usage time periods of the smart button in different mice.

[0010] Furthermore, the method for determining the voice recognition strategy of the mouse is as follows: S11 determines the number of associations between the smart buttons of the mouse and the software modules of the target software based on the association between the smart buttons of the mouse and the software modules of the target software. S12 determines the usage period of the smart button on the mouse based on the usage data of the smart button; S13 determines the voice recognition strategy of the mouse based on the number of associations between the smart buttons of the mouse and the software modules of the target software and the usage period of the smart buttons of the mouse.

[0011] Furthermore, the method for determining the target identification and update method of the optimized processing strategy in the mouse jump handling is as follows: S41 uses the mouse that adopts the basic jump strategy as the available identification mouse, determines the proportion of the available identification mice among the mice with different mouse jump processing strategies, and uses it as the identification matching ratio. S42 determines the percentage of the recognition deviation process of the available recognition target based on the recognition deviation process of the mouse of the available recognition target; S43 determines the target recognition update method for the optimized processing of the jump processing strategy in the mouse based on the recognition matching ratio and the proportion of the recognition deviation process of the available recognition targets.

[0012] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned mouse-based data processing method when running the computer program.

[0013] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0014] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0015] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0016] Figure 1 This is a flowchart of a mouse-based data processing method; Figure 2 This is a flowchart illustrating the method for determining the speech recognition strategy for a mouse. Figure 3 This is a flowchart illustrating the method for determining the jump processing strategy of smart buttons; Figure 4 It is a framework diagram of a computer system. Detailed Implementation

[0017] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0018] Example 1 like Figure 1 As shown, this application provides a mouse-based data processing method, specifically including: S1 determines the mouse's voice recognition strategy based on the association between the mouse's smart buttons and the target software's software modules, as well as the usage data of the smart buttons. It then determines the smart button's jump processing strategy based on the voice recognition strategies of different mice and the recognition data under different voice content. Furthermore, the association between the smart button and the target software module is determined based on the activation strategy of the target software module corresponding to the voice recognition result of the mouse when the smart button is activated.

[0019] Furthermore, the usage data of the smart button includes the usage time periods of the smart button in different mice.

[0020] Specifically, such as Figure 2 As shown, the method for determining the voice recognition strategy of the mouse is as follows: In this embodiment, based on the association between the mouse's smart buttons and the target software modules, the degree of need for the mouse to use smart buttons for jump processing is determined. Furthermore, by combining the usage data of different smart buttons, the reliability of the current voice recognition processing using smart buttons is determined. Based on the degree of need for jump processing and the reliability of the voice recognition processing, the mouse's voice recognition strategy is determined. This reduces unnecessary voice recognition processing and lays the foundation for optimizing the jump strategy based on the reliability of the mouse's voice recognition processing.

[0021] S11 determines the number of associations between the smart buttons of the mouse and the software modules of the target software based on the association between the smart buttons of the mouse and the software modules of the target software.

[0022] The smart button refers to a programmable button configured on the mouse to trigger a specific function; the target software refers to the target application that requires voice recognition and navigation processing; the software module refers to a functional unit in the target software that has a specific function; and the number of associations refers to the number of mapping relationships established between the smart buttons of the mouse and the software modules of the target software.

[0023] Suppose a user's mouse is configured with a smart button, and this smart button is associated with modules B, C, and D of the target software A. Then the number of software modules associated with the mouse's smart button is three.

[0024] This step provides basic data for subsequent assessment of the demand for mouse navigation. Its significance lies in quantifying the complexity of smart button usage by statistically analyzing the number of associated functions, thereby providing a basis for determining the voice recognition strategy.

[0025] It is understandable that if the number of associations between the smart buttons of the mouse and the software modules of the target software exceeds a preset association threshold, then in order to ensure the reliability of the mouse's recognition during the speech recognition process, speech recognition processing will be performed regardless of whether the smart buttons are enabled.

[0026] The preset association threshold refers to the upper limit of the number of smart buttons associated with software modules, which is used to determine whether the complexity of using the smart buttons meets the standard that requires full voice recognition; the statement that voice recognition processing is performed regardless of whether the smart buttons are turned on means that the voice recognition function is triggered as long as there is copying behavior in any mouse operation state.

[0027] Suppose that a mouse's smart buttons are associated with five software modules of the target software, and the preset threshold for the number of associations is three. Since five is greater than three, the mouse needs to perform voice recognition processing regardless of whether the smart buttons are enabled.

[0028] This step triggers the full-time voice recognition mode by setting a threshold for the number of associated elements. Its significance lies in ensuring the reliability of the jump process through full-process voice recognition when the demand for smart button jumps is high, and avoiding jump errors caused by missed recognition.

[0029] Additionally, it can be understood that if the number of associations between the smart buttons of the mouse and the software modules of the target software is not greater than a preset association number threshold, the process proceeds to step S12.

[0030] When the number of associated keys is not greater than the preset threshold, it indicates that the demand for smart button navigation is at a medium or low level. In this case, it is necessary to further combine the actual usage data of the smart button to determine the voice recognition strategy.

[0031] This decision step establishes a logical transition from S11 to S12. Its significance lies in assigning the mouse to different strategies to determine the path based on the different numbers of associations, ensuring that the determination of the speech recognition strategy takes into account both functional complexity and actual usage.

[0032] S12 determines the usage period of the smart button on the mouse based on the usage data of the smart button.

[0033] The usage data of the smart button refers to the data records reflecting the actual usage of the smart button, including information such as usage frequency, usage duration, and usage time period distribution; the usage time period of the smart button refers to the continuous time interval during which the smart button is in an active usage state.

[0034] Furthermore, the usage period of the smart button on the mouse is a unit time period in which the number of times it is used exceeds a preset usage threshold.

[0035] The preset usage threshold refers to the minimum number of times the smart button is triggered within a unit time period, which is used to filter out time periods with actual usage value.

[0036] Suppose that the smart button of a mouse is used a total of 120 times in a day, of which 35 times are used in the hour from 9:00 to 10:00 AM, 40 times in the hour from 2:00 to 3:00 PM, and no more than 20 times in other time periods. The preset usage threshold is 25 times. Then the usage time of the smart button of the mouse is the two hours from 9:00 to 10:00 AM and from 2:00 to 3:00 PM.

[0037] This step determines the actual active periods of the smart button by statistically analyzing the usage data. Its significance lies in identifying the time windows in which users truly and frequently use the smart button, thereby providing data support at the user behavior level for determining subsequent voice recognition strategies.

[0038] Specifically, the above steps include the following: determining the duration percentage of the use of the smart buttons of the mouse based on the usage time periods of different smart buttons, and determining whether the duration percentage of the use of the smart buttons of the mouse is above a preset duration percentage threshold. If so, the voice recognition strategy of the mouse is determined to be to perform voice recognition processing only when the smart buttons are turned on. If not, proceed to step S13.

[0039] The usage period duration percentage refers to the proportion of the cumulative usage time of the mouse's smart buttons to the total monitoring time; the preset duration percentage threshold refers to the lower limit value of the preset usage period percentage, used to determine whether the usage frequency of the smart buttons is frequent enough.

[0040] Suppose that a mouse's smart button is used for a total of six hours in a 24-hour period. The usage time percentage is six divided by twenty-four, which equals 0.25. The preset usage time percentage threshold is 0.20. Since 0.25 is greater than 0.20, the voice recognition strategy for this mouse is determined to be to perform voice recognition processing only when the smart button is activated.

[0041] This judgment step determines whether to adopt a lightweight voice recognition strategy by comparing the usage period ratio with a preset threshold. Its significance is that when the smart button is used frequently, it can adopt a method of recognizing only when it is turned on, thereby reducing unnecessary resource consumption and ensuring the recognition reliability when the user actually uses it.

[0042] S13 determines the voice recognition strategy of the mouse based on the number of associations between the smart buttons of the mouse and the software modules of the target software and the usage period of the smart buttons of the mouse.

[0043] This step combines the number of associations in S11 and the usage period in S12 to determine the final speech recognition strategy, completing the entire analysis chain from functional complexity to user behavior to strategy matching.

[0044] This step determines the voice recognition strategy through multi-dimensional comprehensive judgment. Its significance lies in ensuring that the determination of the strategy takes into account both the functional configuration of the smart button and the frequency and habits of the user in actually using the function, thereby achieving personalized and accurate matching of the voice recognition strategy.

[0045] Specifically, in the above steps, mice that only perform voice recognition processing when the smart button is turned on are selected as screening mice. Based on the proportion of the screening mice among all mice and the number of associations between the smart buttons of the mice and the software modules of the target software, a recognition matching coefficient is determined. It is then determined whether the recognition matching coefficient is greater than a preset matching coefficient threshold. If not, the voice recognition strategy for the remaining mice is determined to perform voice recognition processing regardless of whether the mouse is turned on or not. If so, the voice recognition strategy for the remaining mice is determined to perform voice recognition processing only when the smart button is turned on.

[0046] The screened mice refer to the group of mice that have been identified in step S12 as only performing voice recognition processing when the smart button is turned on; the recognition matching coefficient refers to a risk assessment index that comprehensively reflects the proportion of screened mice and the number of associated mice, and is used to determine whether the remaining mouse group needs enhanced voice recognition; the preset matching coefficient threshold refers to a pre-set critical value of the recognition matching coefficient.

[0047] Suppose that out of a batch of one hundred mice, forty mice are selected for recognition after the aforementioned steps. The proportion of these selected mice in the total number of mice is forty divided by one hundred, which equals 0.40. Further assuming that the batch of mice has three associated mice, the overall matching coefficient is 0.40 divided by 3, which equals 0.13. With a preset matching coefficient threshold of 0.1, and since 0.13 is greater than 0.1, the remaining sixty mice will be subject to a voice recognition strategy where voice recognition is only performed when the smart button is activated.

[0048] This step achieves precise strategy allocation for the remaining mouse users by constructing recognition matching coefficients. Its significance lies in dynamically adjusting the voice recognition strategy of individual mice based on the usage characteristics of the overall user group, which ensures both the convenience of high-frequency users and the recognition reliability of low-frequency users.

[0049] Furthermore, the higher the proportion of the selected mouse among all mice, and the fewer the number of associations between the smart buttons of the mouse and the software modules of the target software, the higher the identification matching coefficient.

[0050] This relationship definition clarifies the calculation logic of the identification matching coefficient. That is, when the proportion of high-frequency mice is higher and the overall number of associated mice is smaller, the identification matching coefficient is higher, indicating that the remaining mouse group is more inclined to adopt a lightweight identification strategy.

[0051] Specifically, such as Figure 3 As shown, the method for determining the jump processing strategy of the smart button is as follows: In this embodiment, the recognition deviation risk of the mouse under different voice content is determined based on the different speech recognition strategies of the mouse and the recognition consistency under different voice content. The worse the recognition consistency, the fewer mice that perform speech recognition processing regardless of whether the mouse is turned on, and the higher the recognition deviation risk. The recognition deviation risk is used to determine the jump processing strategy, which avoids unnecessary jump processing and also ensures that the jump processing is linked to user needs.

[0052] Based on the voice recognition strategies of different mice, S21 identifies mice that perform voice recognition processing regardless of whether the mouse is turned on or off, and uses these mice as reliable recognition mice.

[0053] The reliable recognition mouse refers to a mouse that performs voice recognition regardless of whether the smart button is enabled. Because such mice have full voice recognition capabilities, they have high recognition reliability during the jump process.

[0054] Suppose that out of a batch of one hundred mice, forty of them are determined to perform voice recognition processing regardless of whether the smart button is enabled. These forty mice are considered reliable recognition mice.

[0055] This step, by selecting a group of mice with full recognition capabilities, provides a highly reliable benchmark for determining subsequent jump processing strategies. Its significance lies in using a reliably recognized mouse as a reference to judge the recognition deviation of other mice.

[0056] S22 determines the degree of recognition consistency under different voice content based on the mouse's recognition data, and determines the recognition deviation process based on the degree of recognition consistency.

[0057] The recognition data refers to the recognition result data generated after the mouse performs speech recognition on the speech content; the recognition consistency refers to the degree of consistency between the recognition results generated for the same speech content in different recognition processing processes; the recognition deviation process refers to the recognition processing process with inconsistent recognition results.

[0058] Suppose a mouse performs five recognition processes on the same audio content, resulting in five recognition results. Three of these results are completely consistent, while two results differ. The two discrepancies in the recognition process are the recognition deviation process.

[0059] This step determines the recognition deviation process by analyzing the degree of consistency in recognition. Its significance lies in quantifying the reliability of the mouse's voice recognition and providing data support for subsequent adjustments to the jump processing strategy.

[0060] Specifically, the above steps include the following: S221 Based on the recognition deviation process in different mice, determine the proportion of the recognition deviation process of the mouse in the recognition process, and use the proportion of the recognition deviation process of the mouse in the recognition process as the recognition deviation process proportion. Determine whether there is a mouse whose recognition deviation process proportion is greater than a preset deviation process proportion threshold. If yes, proceed to step S222. If no, determine that the jump processing strategy of the smart button is the basic jump strategy. That is, as long as the number of recognition processing processes corresponding to the same recognition result is the largest in the recognition process, when the user clicks the smart button, the recognition result of the voice with the largest number of recognition processing processes will be used to perform the corresponding software module jump processing.

[0061] The percentage of recognition deviation processes refers to the proportion of the number of recognition deviation processes of a certain mouse to the total number of recognition processes of that mouse; the preset deviation process percentage threshold refers to the upper limit of the pre-set recognition deviation process percentage; the basic jump strategy refers to the default strategy of using the recognition result that appears most frequently during the recognition process as the basis for jump.

[0062] Suppose that in a batch of one hundred mice, after statistical analysis, it is found that the proportion of recognition deviation processes for all mice does not exceed the preset deviation process proportion threshold of 0.15. Then, it is determined that the smart button jump processing strategy for all mice is the basic jump strategy. That is, when the user clicks the smart button, the system selects the voice recognition result that appears most frequently in the recognition process and performs the corresponding software module jump processing.

[0063] This judgment step determines whether an advanced jump processing strategy needs to be adopted by comparing the proportion of the identification deviation process with a preset threshold. Its significance is that when the identification deviation is low, the basic jump strategy is adopted by default to ensure the efficiency and stability of the jump processing, while also ensuring that it is linked to user needs.

[0064] S222 identifies mice with a proportion of identification deviation processes greater than a preset deviation process proportion threshold as mice with identification deviation risk. It then determines whether the proportion of mice with identification deviation risk among all mice is greater than the preset deviation risk proportion threshold. If so, it determines that the jump processing strategy of the smart button is that as long as the identification process is not a identification deviation process, the corresponding software module jump processing is performed using the voice recognition result when the user clicks the smart button. If not, it proceeds to step S23.

[0065] The "recognition deviation risk mouse" refers to a mouse whose recognition deviation rate exceeds a threshold, indicating a risk to the reliability of its voice recognition. The "preset deviation risk rate threshold" refers to a pre-set upper limit for the proportion of mice with recognition deviation risks. The "non-deviation process jump strategy" refers to a strategy that only executes a jump when the recognition result does not belong to a known deviation process.

[0066] Suppose that out of a batch of one hundred mice, fifteen mice have a recognition deviation rate greater than a preset deviation rate threshold of 0.15, and are therefore identified as mice with recognition deviation risk. The percentage of mice with recognition deviation risk in all mice is fifteen divided by one hundred, which equals 0.15. The preset deviation risk rate threshold is 0.10. Since 0.15 is greater than 0.10, the smart button jump handling strategy for all mice is determined to be a non-deviation process jump strategy. That is, when the user clicks the smart button, the system determines whether the current recognition process belongs to a recognition deviation process, and only executes jump processing if it does not belong to a deviation process.

[0067] This judgment step determines whether a more cautious jump strategy needs to be adopted by analyzing the proportion of mice with identified deviation risks. Its significance lies in improving the accuracy of jump processing by eliminating deviations when the proportion of identified mice with identified deviation risks is too high.

[0068] Furthermore, the recognition deviation process refers to the recognition process in which the recognition results of different recognition processes are inconsistent for the same audio content. Specifically, the mouse performs recognition processing at least 3 times for the same audio content. If there are inconsistent recognition results between recognition processes in the same recognition process, then the recognition process is determined to be a recognition deviation process.

[0069] This definition clarifies the criteria for judging a recognition deviation process: the same speech content must be processed at least three times, and if there is any inconsistency between the results of these three processes, the recognition process is judged to be a recognition deviation process.

[0070] S23, based on the reliable mouse data and the recognition deviation process in different mice, determine the jump processing strategy of the smart button.

[0071] This step combines the recognition reliability of a reliable mouse with the recognition deviation process of different mice to determine the final jump processing strategy, which is a further refinement of the jump strategy after steps S21 to S222.

[0072] Suppose that after the analysis of the aforementioned steps, it is found that the recognition data of the reliable mouse is well representative of the overall mouse, and the distribution of the recognition deviation process shows a certain regularity. At this point, it is necessary to combine this information to determine the jump processing strategy.

[0073] This step determines the jump processing strategy through multi-dimensional data analysis. Its significance lies in ensuring that the strategy determination takes into account both the demonstration effect of reliable mouse recognition and the recognition deviation characteristics of different mice, thereby achieving personalization and precision of the jump processing strategy.

[0074] Furthermore, based on the reliable mouse data and the recognition deviation process in different mice, the jump processing strategy for the smart button is determined, specifically including: S231 determines whether the proportion of the reliable mouse in all mice is greater than the preset reliable mouse proportion threshold. If so, the jump processing strategy of the smart button is determined to be that as long as the number of recognition processing processes corresponding to the same recognition result is the largest, when the user clicks the smart button, the recognition result of the voice with the largest number of recognition processing processes is used to perform the corresponding software module jump processing. If not, proceed to step S232.

[0075] The reliable mouse percentage threshold refers to the lower limit of the proportion of reliable mice among all mice, which is used to determine whether the group of reliable mice is sufficiently representative.

[0076] This decision-making step determines whether to adopt a majority-based jump strategy by comparing the proportion of reliably identified mouse cursors. The significance of this is that when the reliably identified mouse cursors are sufficiently representative, the accuracy of the majority results can be trusted, thus allowing for the adoption of a simple and efficient basic jump strategy.

[0077] S232, based on the proportion of the reliable recognition mouse among all mice and the average proportion of recognition deviation processes among different mice, determine the voice recognition risk value of the mouse, and determine whether the voice recognition risk value of the mouse is greater than a preset risk threshold. If so, determine that the jump processing strategy of the smart button is that as long as the recognition process is not a recognition deviation process, when the user clicks the smart button, the corresponding software module jump processing is performed using the voice recognition result. If not, determine that the jump processing strategy of the smart button is that as long as the number of recognition processing processes corresponding to the same recognition result is the largest, when the user clicks the smart button, the corresponding software module jump processing is performed using the voice recognition result with the largest number of recognition processing processes.

[0078] The speech recognition risk value refers to a risk assessment index that comprehensively reflects the average of the percentage of reliable mouse recognition and the percentage of recognition deviation, and is used to quantify the overall speech recognition reliability. It is determined based on the average of the difference between the percentage of reliable mouse recognition and 1 minus the average percentage of recognition deviation. The preset risk threshold refers to the upper limit of the speech recognition risk value that is set in advance.

[0079] Specifically, the higher the proportion of reliable recognition mice among all mice, and the lower the average proportion of recognition deviation processes among different mice, the smaller the voice recognition risk value of the mouse, which ranges from 0 to 1.

[0080] This relationship definition clarifies the calculation logic of the speech recognition risk value: the higher the percentage of reliable mouse recognition, the better the overall recognition reliability; the lower the average percentage of recognition deviation, the less severe the recognition deviation. Both factors together determine the magnitude of the speech recognition risk value.

[0081] Assuming that out of a batch of one hundred mice, the percentage of mice that can be reliably recognized is 0.30, and the average percentage of recognition deviations among different mice is 0.08, then the comprehensive risk value for voice recognition is calculated as (0.3 + 0.2) / 2, which equals 0.25.

[0082] S2 performs different mouse jump control processing under smart buttons based on the jump processing strategy, and determines the suspected abnormal jump data of the mouse based on the mouse operation data after jump processing. When it is determined that the jump processing strategy needs to be optimized and adjusted based on the suspected abnormal jump data, proceed to the next step. Furthermore, the suspected abnormal jump data is determined based on the number of times the mouse closes the target software module within the target duration after jumping to it, i.e., the number of suspected abnormal jumps.

[0083] The number of suspected abnormal jumps refers to the number of times a mouse user clicks a smart button to jump to the target software module, but then closes the software module within a short period of time. This is used to reflect erroneous jumps caused by identification errors.

[0084] Suppose a user clicks a smart button and is redirected to target software A, but closes software A within 5 seconds of the redirection. This situation, where the target is closed within a short period of time, is counted as a suspected abnormal redirection, indicating that it does not match the user's needs.

[0085] This step quantifies abnormal situations in redirection handling by counting the number of suspected abnormal redirects. Its significance lies in providing a quantitative basis for subsequent judgment on whether redirection handling strategies need to be optimized.

[0086] Specifically, determining that the jump handling strategy needs optimization and adjustment includes: S31 determines the number of suspected abnormal jumps in different mice based on the suspected abnormal jump data.

[0087] This step involves statistical analysis of the number of suspected abnormal jumps for each mouse, establishing a quantitative profile of abnormal jump behavior.

[0088] Suppose that in the last 24 hours, a batch of 100 mice experienced a total of 200 suspected abnormal jumps, of which mouse A experienced 5 jumps, mouse B experienced 3 jumps, mouse C experienced 7 jumps, and the remaining mice experienced no more than 2 suspected abnormal jumps.

[0089] This step involves statistical analysis of suspected abnormal jump data. Its significance lies in identifying individual mouse cursors with prominent abnormal jump behavior, providing data support for subsequent optimization decisions.

[0090] S32 determines whether the jump handling strategy needs to be optimized or adjusted based on the number of suspected abnormal jumps in different mice.

[0091] This step determines whether strategy optimization is needed by comparing the number of suspected abnormal jumps with a preset threshold, thus establishing a triggering mechanism from anomaly detection to strategy adjustment.

[0092] Specifically, when the average number of suspected abnormal jumps by different mice within the most recent preset time period is greater than the preset abnormal number threshold, there is a risk that the mouse may make an erroneous jump due to voice recognition deviation. Therefore, it is determined that the jump processing strategy needs to be optimized and adjusted.

[0093] The preset abnormal number threshold refers to the upper limit of the average number of suspected abnormal jumps, which is used to determine whether there is a systematic identification bias in the overall jump processing.

[0094] This judgment step determines whether to trigger the policy optimization process by comparing the average number of suspected abnormal jumps with a preset threshold. Its significance lies in the timely activation of the optimization mechanism to improve the efficiency of training data updates when abnormal jump behavior becomes widespread.

[0095] S3 determines the recognition deviation process in the mouse based on recognition data under different speech content, and determines the recognition update method of the optimized processing target of the jump processing strategy in the mouse based on different mouse jump processing strategies and the recognition deviation process of the mouse using the basic jump strategy.

[0096] Specifically, the method for determining the identification and update method of the optimization processing target of the mouse jump processing strategy is as follows: In this embodiment, the timeliness of updating training data using mice employing the basic jump strategy is determined based on the proportion of mice using the basic jump strategy and the recognition deviation process of mice with different available recognition targets. The higher the proportion of mice using the basic jump strategy and the greater the recognition deviation process of mice with different available recognition targets, the higher the timeliness of updating training data. The timeliness of updating training data is then used to determine the method for optimizing the jump processing strategy in the mouse and the target recognition update method, laying the foundation for a balanced control of the reliability of jump processing and the reliability of updating training data.

[0097] S41 identifies mice that use a basic jump strategy as available mice for recognition, determines the proportion of available mice for recognition among the mice using different mouse jump processing strategies, and uses this proportion as the recognition matching ratio.

[0098] The term "available identifiable mouse" refers to a mouse that employs a basic jump strategy. Such mice exhibit good stability during the identification process and are suitable as a source of training data. The term "identification matching ratio" refers to the proportion of available identifiable mice to the total number of mice.

[0099] If, out of a batch of one hundred mice, sixty mice use the basic jump strategy, then the matching ratio is sixty divided by one hundred, which equals 0.60.

[0100] This step assesses the basic availability of training data by statistically analyzing the proportion of recognizable mice. Its significance lies in providing benchmark data for subsequent judgments on whether reliable training data updates are possible.

[0101] It is understood that the above steps include the following: determining whether the recognition matching ratio is greater than the preset matching ratio threshold. If so, the reliability of using the suspected abnormal jump data of the available recognition target to perform the recognition processing of the mouse's speech recognition model training data is relatively high. That is, once a suspected abnormal jump occurs, the reliability of using the corresponding speech as training data to construct the training set is relatively high. Therefore, the method for determining the recognition update of the target of the optimized processing of the jump processing strategy in the mouse is as follows: for a mouse that is not a usable recognition target, as long as its recognition deviation process ratio is less than the preset value of the deviation process ratio, it is regarded as a usable recognition target. On the one hand, this avoids suspected abnormal jumps as much as possible, and on the other hand, it ensures the efficiency of updating the training data. If not, proceed to step S42.

[0102] The preset value of the deviation process ratio refers to the upper limit of the pre-set identification deviation process ratio, which is used to determine whether a mouse can be included in the range of available identification targets.

[0103] Assuming the matching ratio is 0.60 and the preset matching ratio threshold is 0.55, since 0.60 is greater than 0.55, the method for updating the target identification is determined as follows: for mice that are not available targets, as long as their identification deviation ratio is less than the preset deviation ratio value of 0.10, they are considered as available targets.

[0104] This judgment step determines whether to adopt a more lenient standard for including available targets by comparing the matching ratio with a preset threshold. Its significance is that when the mouse usage rate of the basic jump strategy is high enough, a higher tolerance for deviation can be adopted to expand the range of available targets.

[0105] S42, determine the percentage of the recognition deviation process of the available recognition target based on the recognition deviation process of the mouse of the available recognition target.

[0106] After determining the range of available mice in S41, this step further analyzes the recognition deviations of these mice to provide accuracy support for determining the subsequent update method.

[0107] Suppose that a certain usable mouse has a total of 300 recognition deviation processes, and the total number of recognition processes of the mouse is 6,000, then the percentage of recognition deviation processes is 300 divided by 6,000, which equals 0.05.

[0108] This step quantifies the recognition reliability of such mice by calculating the proportion of recognition deviation in the available recognition process. Its significance lies in providing an accurate basis for judging the efficiency of training data updates.

[0109] The above steps include the following: Based on the recognition deviation process ratio of different available recognition targets, determine whether the average value of the recognition deviation process ratio of different available recognition targets is less than a preset value of the deviation process ratio. If so, then on the one hand, the number of available recognition targets is small, and on the other hand, the recognition deviation process ratio is low, resulting in a slow update efficiency of training data. Therefore, the method for optimizing the recognition update of the target of the jump processing strategy in the mouse is to determine that for a mouse that is not a available recognition target, as long as its recognition deviation process ratio is less than the second preset value of the deviation process ratio, it is regarded as a available recognition target.

[0110] It should be noted that the preset value of the second deviation process ratio is greater than the preset value of the deviation process ratio.

[0111] The second deviation process ratio preset value refers to a more lenient threshold value relative to the deviation process ratio preset value, which is used to expand the scope of available identification targets in specific situations.

[0112] Assume the average recognition deviation ratio of sixty usable mice is 0.05, the preset value of the deviation ratio is 0.10, and the preset value of the second deviation ratio is 0.15. Since 0.05 is less than 0.10, the recognition update method for the optimization target is determined as follows: for mice that are not usable targets, as long as their recognition deviation ratio is less than 0.15, they will be considered usable targets.

[0113] This judgment step determines whether a more lenient inclusion standard needs to be adopted by comparing the average proportion of the identification deviation process with a preset threshold. Its significance lies in expanding the range of available identification targets as much as possible to improve the update efficiency of training data while ensuring the reliability of identification.

[0114] S43 determines the target recognition update method for the optimized processing of the jump processing strategy in the mouse based on the recognition matching ratio and the proportion of the recognition deviation process of the available recognition targets.

[0115] This step combines two dimensions—the recognition matching ratio of S41 and the proportion of recognition deviation in S42—to determine the final recognition update method.

[0116] This step determines the identification and update method through multi-dimensional comprehensive judgment. Its significance lies in ensuring that the update of training data takes into account both the coverage of available targets and the reliability of identification, thereby achieving accurate identification of optimized targets.

[0117] Specifically, the above steps include the following: S431, determine whether the recognition matching ratio is less than the preset matching ratio preset value. If yes, determine the recognition update method of the optimized processing target of the jump processing strategy in the mouse as follows: for a mouse that is not a usable recognition target, as long as its recognition deviation process ratio is less than the second deviation process ratio preset value, it will be regarded as a usable recognition target. If not, proceed to step S432.

[0118] The preset matching ratio preset value refers to a pre-set critical value for the identification matching ratio, which is used to determine whether a lenient inclusion standard needs to be adopted.

[0119] This judgment step determines whether a lenient standard needs to be adopted by comparing the identification matching ratio with a preset value. Its significance lies in ensuring the sufficiency of training data by expanding the range of available identification targets when the identification matching ratio is low.

[0120] S432, a mouse whose identification deviation process ratio is not less than a preset deviation process ratio preset value is selected as a filter matching mouse. It is determined whether the proportion of the filter matching target in the available identification mice is greater than a preset filter proportion threshold. If so, the identification update method for the optimized processing target of the jump processing strategy in the mouse is determined as follows: for a mouse that is not a usable identification target, as long as its identification deviation process ratio is less than the preset deviation process ratio preset value, it is selected as a usable identification target. If not, for a mouse that is not a usable identification target, for a mouse whose smart button usage time duration is greater than or equal to a preset duration proportion threshold, as long as its identification deviation process ratio is less than a second deviation process ratio preset value, it is selected as a usable identification target. For a mouse whose smart button usage time duration is not greater than or equal to a preset duration proportion threshold, as long as its identification deviation process ratio is less than the preset deviation process ratio preset value, it is selected as a usable identification target.

[0121] The selected matching mouse refers to a mouse whose identification deviation ratio is not lower than a preset threshold, indicating that its training data update efficiency is high; the preset selection ratio threshold refers to the upper limit of the proportion of selected matching mice among the available identification mice.

[0122] This judgment step determines the specific inclusion criteria by analyzing the proportion of matched mouse cursors. Its significance lies in using a more refined classification standard when the proportion of matched mouse cursors is high, and using a uniform standard when the proportion of matched mouse cursors is low, thereby achieving dynamic adaptation for the identification of available targets.

[0123] Example 2 Secondly, such as Figure 4As shown, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described mouse-based data processing method when running the computer program.

[0124] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0125] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0126] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A mouse-based data processing method, characterized by, Specifically, it includes: The speech recognition strategy for the mouse is determined based on the association between the smart buttons of the mouse and the software modules of the target software, as well as the usage data of the smart buttons. The jump processing strategy for the smart buttons is determined based on the speech recognition strategies of different mice and the recognition data under different speech content. Based on the jump processing strategy, different mouse jump control processing is performed under smart buttons, and based on the mouse operation data after jump processing, suspected abnormal jump data of the mouse is determined. If it is determined that the jump processing strategy needs to be optimized and adjusted based on the suspected abnormal jump data, proceed to the next step. The recognition deviation process in the mouse is determined by recognition data under different speech content. Based on the recognition deviation process of different mouse jump processing strategies and the mouse using the basic jump strategy, the recognition update method for optimizing the processing target of the jump processing strategy in the mouse is determined. The recognition deviation process refers to the recognition process in which the recognition results of different recognition processes are inconsistent for the same speech content. If there are inconsistent recognition results between different recognition processes in the same recognition process, then the recognition process is determined to be a recognition deviation process. The basic jump strategy is that if the number of recognition processes corresponding to the same recognition result is the largest, then when the user clicks the smart button, the recognition result of the voice with the largest number of recognition processes will be used to jump to the corresponding software module.

2. The mouse-based data processing method according to claim 1, wherein, The association between the smart button and the target software module is determined based on the activation strategy of the target software module corresponding to the voice recognition result based on the mouse when the smart button is activated.

3. The mouse-based data processing method according to claim 1, wherein, The usage data of the smart button includes the usage time periods of the smart button in different mice.

4. The mouse-based data processing method as described in claim 1, characterized in that, The method for determining the speech recognition strategy of the mouse is as follows: The number of associations between the smart buttons of the mouse and the software modules of the target software is determined based on the association between the smart buttons of the mouse and the software modules of the target software. Based on the usage data of the smart buttons, the usage period of the smart buttons on the mouse is determined; The voice recognition strategy of the mouse is determined based on the number of associations between the smart buttons of the mouse and the software modules of the target software, as well as the usage period of the smart buttons of the mouse.

5. The mouse-based data processing method as described in claim 4, characterized in that, If the number of associations between the smart buttons of the mouse and the software modules of the target software exceeds a preset association threshold, then in order to ensure the reliability of the mouse's recognition during the speech recognition process, speech recognition processing will be performed regardless of whether the smart buttons are enabled.

6. The mouse-based data processing method as described in claim 4, characterized in that, The smart button on the mouse is used for a period of time when the number of uses exceeds a preset threshold.

7. The mouse-based data processing method as described in claim 1, characterized in that, The method for determining the jump processing strategy of the smart button is as follows: Based on the speech recognition strategies of different mice, mice that perform speech recognition processing regardless of whether the mouse is turned on are identified and used as reliable recognition mice. Based on the mouse recognition data under different voice content, determine the degree of recognition consistency under different voice content, and determine the recognition deviation process based on the degree of recognition consistency; Based on the reliable mouse recognition data and the recognition deviation process in different mice, the jump processing strategy of the smart button is determined.

8. The mouse-based data processing method as described in claim 7, characterized in that, The recognition deviation process refers to the recognition process in which the recognition results are inconsistent between different recognition processing processes for the same audio content.

9. The mouse-based data processing method as described in claim 1, characterized in that, The method for determining the target identification and update method of the optimized processing strategy in the mouse jump handling is as follows: The mice that adopt the basic jump strategy are used as the available mice for identification. The proportion of available mice for identification is determined by different mouse jump processing strategies and used as the identification matching ratio. The percentage of the recognition deviation process of the available identifiable targets is determined based on the recognition deviation process of the mouse for the available identifiable targets. Based on the recognition matching ratio and the proportion of recognition deviation process of the available recognition targets, the method for optimizing the recognition update of the target in the jump processing strategy of the mouse is determined.

10. A computer system, comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a mouse-based data processing method according to any one of claims 1-9.

Images