A wearable device sports voice broadcasting method

Abstract

The invention discloses a method for voice broadcasting sports of a wearable device, and belongs to the technical field of voice broadcasting sports of a wearable device. The method comprises: performing voice text retrieval based on voice broadcasting requirements to obtain a plurality of voice materials; analyzing each voice material according to each monitoring item to determine a representative material corresponding to each monitoring item; setting a splicing segment in each representative material to obtain each standard material; performing voice conversion on each standard material to obtain each standard voice segment; setting each single auxiliary audio segment, and storing each single auxiliary audio segment and the standard voice segment as a binary file; setting a broadcasting rule; acquiring each monitoring item data of a target device in real time; identifying monitoring feature data in the monitoring item data, and checking the monitoring feature data according to the broadcasting rule to determine whether the voice broadcasting requirement is met; and performing voice broadcast processing when it is determined that the voice broadcasting requirement is met.

Description

Technical Field

[0001] The present invention belongs to the technical field of sports voice broadcasting of wearable devices, and in particular to a sports voice broadcasting method of a wearable device. Background Art

[0002] With the continuous development of science and technology, wearable devices are increasingly used in the fields of health management and smart sports. These devices are usually equipped with various sensors that can monitor the user's sports data in real time, such as steps, distance, speed, heart rate, etc. In order to improve user experience and health management effects, real-time broadcasting of these sports data has become one of the indispensable functions of wearable devices.

[0003] However, due to the limited resources of wearable devices, traditional speech synthesis models often cannot meet the needs of real-time speech broadcasting. Traditional speech synthesis models require a lot of computing resources and storage space, while the processing power and storage capacity of wearable devices are limited and cannot support the operation of such large speech synthesis models.

[0004] Therefore, in order to overcome this problem, the present invention provides a method for voice broadcasting sports of a wearable device. Summary of the invention

[0005] In order to solve the problems existing in the above-mentioned scheme, the present invention provides a method for voice broadcasting sports of a wearable device.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A method for voice broadcasting sports of a wearable device, the method comprising:

[0008] Step 1: Obtain the voice broadcast requirements of the target device, perform voice text retrieval based on the voice broadcast requirements, and obtain several voice materials; set corresponding monitoring items according to the monitoring function of the target device, analyze each voice material according to each monitoring item, and determine the representative material corresponding to each monitoring item.

[0009] Furthermore, the method for analyzing the classified data of each material according to each monitoring item includes:

[0010] Identifying the storage value corresponding to each of the voice materials;

[0011] Performing reuse evaluation on each of the voice materials to obtain a reuse value and a test value set corresponding to each of the voice materials;

[0012] Determine the matching item corresponding to the corresponding voice material according to the test value set, and mark the matching item on the voice material;

[0013] Classify according to the compliance items corresponding to each voice material to obtain the voice classification data corresponding to each monitoring item, where the voice classification data consists of each voice material;

[0014] Perform pairwise priority comparison on each voice material in the voice classification data to determine the corresponding priority, and sort the voice materials in the voice classification data according to the priority of pairwise comparison between voice materials to obtain the first sequence; use the voice material ranked first in the first sequence as the representative material of the corresponding monitoring item.

[0015] Furthermore, the method for reusing evaluation of voice materials includes:

[0016] Set corresponding simulation data according to each monitoring item, and integrate each simulation data into a test set;

[0017] Establish a replacement judgment model, evaluate the test set and each voice material through the replacement judgment model to obtain the test value set corresponding to each voice material; generate the corresponding test vector according to the test value set;

[0018] According to the formula Calculate the corresponding reuse value;

[0019] In the formula: FY is the reuse value; e is the natural constant; PU is the test vector; K is the number of simulation data in the test set.

[0020] Furthermore, the expression of the replacement judgment model is: ;

[0021] In the formula: s is the voice material and the simulation data; the output data is the replacement judgment value 1 or 0.

[0022] Furthermore, the method for comparing the priorities of two voice materials includes:

[0023] Mark the two voice materials whose priorities need to be compared as the first data and the second data respectively;

[0024] Set the formulas and ;

[0025] In the formula: b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1; QY1 and QY2 are the first priority comparison values and the second priority comparison values corresponding to the first data and the second data respectively; FY1 and FY2 are the reuse values corresponding to the first data and the second data respectively; CZ1 and CZ2 are the storage values corresponding to the first data and the second data respectively;

[0026] When QY1 > QY2, the first data takes precedence over the second data;

[0027] When QY1 < QY2, the second data takes precedence over the first data;

[0028] When QY1 = QY2, the first data and the second data have the same priority.

[0029] Step 2: Set corresponding splicing segments in each representative material, and mark the representative material with the set splicing segments as the standard material; perform voice conversion on each standard material to obtain the standard voice segments corresponding to each monitoring item;

[0030] Step 3: Set each single auxiliary segment, and store each single auxiliary segment and the standard voice segment as a binary file;

[0031] Step 4: Set the broadcast rules; obtain the data of each monitoring item of the target device in real time; identify the monitoring feature data in the monitoring item data, check the monitoring feature data according to the broadcast rules, and determine whether the voice broadcast requirements are met;

[0032] When it is judged that the voice broadcast requirements are not met, no corresponding operation is performed;

[0033] When it is judged that the voice broadcast requirements are met, obtain the standard voice segment corresponding to the monitoring item; perform index analysis on the monitoring feature data to obtain each single value; obtain the corresponding single auxiliary segment according to each single value, splice each single auxiliary segment into the standard voice segment to obtain the target broadcast voice; perform voice broadcast according to the target broadcast voice.

[0034] Furthermore, automatically adjust the voice parameters of the voice broadcast. The method includes:

[0035] Obtain each audio data, establish an equivalent judgment model, and the expression of the equivalent judgment model is ;

[0036] In the formula: q corresponds to two audio data for comparison; the output data is the equivalent judgment value 1 or 0;

[0037] Perform pairwise equivalent analysis on each audio data through the equivalent judgment model to obtain the equivalent judgment values between each audio data, and merge each audio data according to the equivalent judgment values to obtain each representative parameter and the application scenario corresponding to each representative parameter;

[0038] Obtain the user's heart rate data in real time, and determine the corresponding application scenario according to the heart rate data;

[0039] Determine the corresponding representative parameter according to the application scenario; perform corresponding voice broadcast adjustment according to the representative parameter.

[0040] Furthermore, the method for merging each audio data according to the equivalent judgment value includes:

[0041] The audio data with an equivalent judgment value of 0 are merged to obtain each initial classification; the speech parameter corresponding to the audio data with the highest share in the initial classification is marked as the initial parameter;

[0042] Identify the share of each initial category and set the background value corresponding to each initial category;

[0043] Calculate the classification value of each initial classification according to the formula PV=FE×BY;

[0044] In the formula: PV is the classification value; FE is the share ratio; BY is the classification value;

[0045] The initial classification with classification value lower than the threshold X1 is marked as the intermediate classification, and the initial classification with classification value not lower than the threshold X1 is marked as the merged classification;

[0046] According to the initial parameters corresponding to the intermediate classification and each merged classification, determine the merged classification with the smallest difference from the intermediate classification; merge the intermediate classification into the merged classification with the smallest difference to obtain a new merged classification;

[0047] Mark the initial parameters in the merged classification as representative parameters.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] The present invention provides an innovative solution to the contradiction between resource limitation of wearable devices and the demand for real-time voice broadcasting, and has broad application prospects and market promotion value. Through efficient voice splicing, real-time broadcasting of changing motion data in a resource-limited environment is achieved, bringing users a more intelligent and convenient user experience; by writing the processed voice data into an efficient binary (bin) file, it ensures that the space occupied on the resource-limited wearable device is extremely small. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0052] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] like Figure 1 As shown, a method for voice broadcasting sports on a wearable device, the method comprising:

[0054] Step 1: Mark the wearable device as the target device, obtain the voice broadcast requirements of the target device, and determine the specific requirements according to the monitoring function of the target device, such as heart rate monitoring broadcast, step monitoring broadcast, speed monitoring broadcast, distance monitoring broadcast, etc.; perform voice text retrieval according to the voice broadcast requirements, obtain several voice texts, and mark them as voice materials. The voice material is the text data that describes the monitoring data corresponding to each monitoring function, such as "Your current step count is 10,000 steps", "Your current speed is 5 kilometers per hour", where 10,000 steps and 5 kilometers per hour are the monitoring data for the corresponding step monitoring and speed monitoring respectively; set the corresponding monitoring items according to each monitoring function, analyze each voice material according to each monitoring item, and determine the representative material corresponding to each monitoring item.

[0055] Among them, the method of analyzing the classified data of each material according to each monitoring item includes:

[0056] Identify the storage value corresponding to each voice material. The storage value is the storage space required for storing the voice material after it is subsequently converted into voice. Its memory size can be directly estimated. Perform reuse evaluation on each voice material to obtain a reuse value and test value set corresponding to each voice material.

[0057] Determine the monitoring items that the voice material can meet the voice broadcasting requirements according to the test value set, that is, make a judgment according to the simulation data corresponding to the replacement judgment value of 1, mark the corresponding monitoring items as compliant items, and mark the compliant items on the corresponding voice material;

[0058] Classify the voice materials according to the corresponding items, obtain the voice materials corresponding to the monitoring items, and integrate them into the voice classification data corresponding to the monitoring items, that is, classify the voice materials according to the corresponding items, and classify the voice materials into the monitoring items corresponding to the corresponding items. If there are multiple matching items, they will be classified into multiple voice classification data;

[0059] Perform a priority comparison between each voice material in the voice classification data to determine the corresponding priority, sort the priority of each voice material in the voice classification data according to the priority of the comparison between the two voice materials, and obtain a first sequence; and use the voice material ranked first in the first sequence as the representative material of the monitoring item.

[0060] The method for reusing evaluation of voice materials includes:

[0061] Obtain various monitoring data that each monitoring item may have, and mark them as simulated data. There is only one simulated data for one type of monitoring data; integrate each simulated data into a test set; that is, integrate the simulated data corresponding to each monitoring item into a test set;

[0062] Establish a replacement judgment model, which is used to judge whether the voice material meets the voice broadcast requirements after replacing the corresponding monitoring data in the voice material with simulated data, that is, whether it meets the requirements of normal speech after replacing the corresponding simulated data, and use existing voice technologies for judgment. The expression of the replacement judgment model is ; where: s is the voice material and the simulated data, that is, the input data; the output data is the replacement judgment value 1 or 0;

[0063] Evaluate the test set and each voice material according to the replacement judgment model, that is, evaluate one by one whether the replacement of each simulated data in the test set for the voice material meets the voice broadcast requirements, obtain the replacement judgment values corresponding to the voice material and each simulated data, and integrate the replacement judgment values corresponding to each simulated data into the test value set of the voice material; generate a corresponding test vector according to the test value set. For example, if the test value set is {1, 0, 1, 1, 0, 0, 0, 1}, then the test vector is (1, 0, 1, 1, 0, 0, 0, 1);

[0064] According to the formula Calculate the corresponding reuse value; where: FY is the reuse value; e is the natural constant; PU is the test vector; K is the number of simulated data in the test set.

[0065] The method for comparing the priorities of two voice materials includes:

[0066] Mark the two voice materials whose priorities need to be compared as the first data and the second data respectively;

[0067] Set the formulas and ;

[0068] Where: b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1; QY1 and QY2 are the first priority comparison values and the second priority comparison values corresponding to the first data and the second data respectively; FY1 and FY2 are the reuse values corresponding to the first data and the second data respectively; CZ1 and CZ2 are the storage values corresponding to the first data and the second data respectively;

[0069] When QY1 > QY2, the first data takes precedence over the second data;

[0070] When QY1 < QY2, the second data takes precedence over the first data;

[0071] When QY1 = QY2, the first data and the second data have the same priority.

[0072] Step 2: Set corresponding splicing segments in each representative material, that is, remove the part of the material data related to the corresponding monitoring item data, and mark the remaining data segment after removal as the splicing segment for subsequent supplementation of the corresponding monitoring item data, such as step count, speed, etc. data, "Your current step count is XXX steps", "Your current speed is XXX kilometers per hour"; Mark the representative material with the set splicing segment as the standard material; Perform voice conversion on each standard material through manual or other means, that is, record voice according to the standard material to obtain the standard voice segments corresponding to each monitoring item; The standard voice segments of the corresponding monitoring items include the corresponding units and only lack the corresponding numbers.

[0073] Step 3: Set each single auxiliary sound segment, that is, the voice of various single values, generally single voices such as one to ten, hundred, thousand, ten thousand, etc. Because the corresponding values will be indexed and analyzed later, such as input 102.58, output {"one", "hundred", "zero", "two", "point", "five", "eight"}; The input data is the monitoring feature data, and the output data is composed of each single value; Store each single auxiliary sound segment and the standard voice segment as a binary file to save storage space and improve data reading efficiency. This file is embedded in the firmware of the target device for convenient calling and use at any time.

[0074] In one embodiment, since the voice parameters such as the speech rate and pitch of voice announcements in many mobile devices are fixed and cannot be adjusted again after being set by the platform side, or the adjustment is inconvenient; Based on this, in this embodiment, a method for intelligently adjusting voice parameters according to the user's movement scenario and needs is proposed. The method is as follows:

[0075] Obtain various audio data in the movement background. The audio data is the voice parameters and corresponding application scenarios used by people in listening to music and communication in the existing data, such as application scenarios of corresponding movement types such as outdoors, at home, in the gym, etc., and mark the share ratio of each audio data applying this voice parameter in the corresponding application scenario; Analyze each audio data to determine whether it can be regarded as equivalent, that is, the playback effects are the same. Specifically, the platform side sets each sound effect equivalence evaluation standard, marked as the equivalence standard, and represents it in the range of each voice parameter for subsequent judgment. For example, 1-9 of a parameter is regarded as equivalent. If all parameters are equivalent, it is judged to meet the equivalence standard; Based on this, establish an equivalence judgment model. The expression of the equivalence judgment model is ; where: q is the input data, that is, the two audio data to be compared; the output data is the equivalence judgment value 1 or 0;

[0076] By analyzing the equivalent judgment model, the equivalent judgment values ​​between the audio data are obtained, and the audio data are merged according to the equivalent judgment values ​​to obtain the representative parameters and the application scenarios corresponding to the representative parameters;

[0077] Obtain the user's heart rate characteristics in each application scenario, that is, the user's heart rate during exercise in the corresponding application scenario. This is set based on the user's historical exercise data, or the platform can set it based on personnel testing;

[0078] The user's heart rate data is obtained in real time, and the corresponding application scenario is determined according to the heart rate data and each heart rate feature; the corresponding representative parameters are determined according to the application scenario; and the corresponding voice broadcast adjustment is made according to the representative parameters.

[0079] The method for merging the audio data according to the equivalent judgment value includes:

[0080] The audio data with an equivalent judgment value of 0 are merged to obtain each initial classification, that is, the equivalent judgment values ​​between the audio data in the initial classification are all 0; an initial parameter is set for each initial classification, that is, the voice parameter corresponding to the audio data with the highest share in the initial classification;

[0081] Identify the share ratio of each initial classification, that is, the sum of the share ratios corresponding to each audio data, and set the background value corresponding to each initial classification; the background value is the background ratio of the application scenario corresponding to the initial classification in the voice broadcast of the target device;

[0082] The classification value of each initial classification is calculated according to the formula PV=FE×BY; where: PV is the classification value; FE is the share ratio; BY is the classification value;

[0083] The initial classification with classification value lower than the threshold X1 is marked as the intermediate classification, and the initial classification with classification value not lower than the threshold X1 is marked as the merged classification;

[0084] Determine the merged classification with the smallest difference from the intermediate classification, that is, the smallest difference in speech parameters, and compare the differences with the corresponding initial parameters; merge the intermediate classification into the merged classification with the smallest difference to obtain a new merged classification;

[0085] Mark the initial parameters in the merged classification as representative parameters.

[0086] Step 4: The user sets the corresponding voice broadcast requirements according to the needs, that is, what requirements must be met to broadcast the corresponding monitoring item data. For example, at every 1,000 steps, the target device will broadcast the current number of steps in real time to remind the user of the exercise progress; when the speed changes, the current speed is broadcast to help the user adjust the exercise intensity, which is integrated into the broadcast rules; the data of each monitoring item of the target device is obtained in real time; the monitoring feature data in the monitoring item data is identified, and the monitoring feature data is checked according to the broadcast rules to determine whether the voice broadcast requirements are met;

[0087] When it is determined that the voice broadcast requirement is not met, no corresponding operation is performed;

[0088] When it is determined that the voice broadcast requirements are met, the standard voice segment corresponding to the monitoring item is obtained, and the monitoring feature data is indexed and analyzed to obtain each single numerical value; according to each single numerical value, the corresponding single auxiliary sound segment is obtained, and each single auxiliary sound segment is spliced ​​into the standard voice segment to obtain the target broadcast voice; and the target broadcast voice is broadcast.

[0089] For example, the present invention is applied to a smart sports bracelet. When the user is exercising, the bracelet can broadcast data such as the number of steps, distance, speed, heart rate, etc. in real time, effectively improving the user's exercise experience and health management effect. The details are as follows:

[0090] Voice clip processing: The development team first recorded voice clips containing various sports data, such as "Your current step count is XXX steps", "Your current speed is XXX kilometers per hour", etc. These voice clips were carefully processed, adjusting parameters such as speech speed and intonation to ensure voice quality and fluency.

[0091] 2. Voice clip storage: The processed voice clips are stored as binary (bin) files to save storage space and improve data reading efficiency. This file is embedded in the firmware of the smart sports bracelet for easy call and use at any time.

[0092] 3. Data spelling standardization: An intelligent spelling standardization logic is designed to convert the received exercise data into a standard spelling voice array index. For example, when the step data is received, it is converted into the corresponding step voice segment index.

[0093] Voice broadcast splicing rules: Advanced voice broadcast splicing rules have been written to take voice fragments from binary files according to the spelling voice array index and splice the voice fragments according to the set rules and order.

[0094] Real-time broadcast application scenario: When users wear smart sports bracelets and exercise, the bracelets can monitor exercise data in real time and trigger voice broadcasts. For example, every 1,000 steps, the bracelet will splice and broadcast the current number of steps in real time to remind users of exercise progress; when the speed changes, it broadcasts the current speed to help users adjust exercise intensity.

[0095] A wearable device comprises:

[0096] Memory for storing computer programs;

[0097] A processor is used to implement the steps of the method in the above embodiment (a method for voice broadcasting sports on a wearable device) when executing a computer program.

[0098] Among them, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 31 can be implemented in at least one hardware form of a digital signal processor (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor may be integrated with a graphics processing unit (GPU), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0099] The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include high-speed random access memory, and non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory is at least used to store the following computer program, wherein, after the computer program is loaded and executed by the processor, it can implement the relevant steps of the wearable device motion voice broadcast method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory may also include an operating system and data, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system may include Windows, Unix, Linux, etc. The data may include but is not limited to the data involved in the method for implementing the wearable device motion voice broadcast, etc.

[0100] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0101] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0102] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, is also included in the patent protection scope of the present invention.

[0103] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0104] For the convenience of description, the above devices are described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in one or more software and / or hardware. It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0105] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 The functionality specified in one or more boxes.

[0106] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A function specified in a process or multiple boxes.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

Claims

1. A wearable device sports voice broadcasting method, characterized in that: Methods include: Step 1: Obtain the voice broadcast requirements of the target device, perform voice text retrieval based on the voice broadcast requirements, and obtain several voice materials; Setting corresponding monitoring items according to the monitoring function of the target device, analyzing each of the voice materials according to each of the monitoring items, and determining representative materials corresponding to each of the monitoring items; Step 2: Set a corresponding splicing segment in each representative material, and mark the representative material with the splicing segment as the standard material; perform voice conversion on each standard material to obtain a standard voice segment corresponding to each monitoring item; Step 3: setting each single auxiliary audio segment, and storing each single auxiliary audio segment and the standard voice segment as a binary file; Step 4: Set the broadcast rules; obtain the monitoring item data of the target device in real time; identify the monitoring feature data in the monitoring item data, check the monitoring feature data according to the broadcast rules, and determine whether the voice broadcast requirements are met; When it is determined that the voice broadcast requirement is not met, no corresponding operation is performed; When it is determined that the voice broadcast requirements are met, the standard voice segment corresponding to the monitoring item is obtained; the monitoring feature data is indexed and analyzed to obtain each single value; the corresponding single auxiliary sound segment is obtained according to each single value, and each single auxiliary sound segment is spliced ​​into the standard voice segment to obtain the target broadcast voice; the voice broadcast is performed according to the target broadcast voice; Methods for analyzing the classified data of each material according to each monitoring item include: Identifying the storage value corresponding to each of the voice materials; Performing reuse evaluation on each of the voice materials to obtain a reuse value and a test value set corresponding to each of the voice materials; Determine the matching item corresponding to the corresponding voice material according to the test value set, and mark the matching item on the voice material; Classify the corresponding items according to the voice materials to obtain voice classification data corresponding to the monitoring items, wherein the voice classification data is composed of the voice materials; Comparing the priorities of the voice materials in the voice classification data in pairs, determining the corresponding priorities, and sorting the priorities of the voice materials in the voice classification data according to the priorities of the comparison between the voice materials in pairs, to obtain a first sequence; and using the voice material ranked first in the first sequence as the representative material of the corresponding monitoring item; Methods for evaluating the reuse of voice materials include: According to the simulation data corresponding to each monitoring item, each simulation data is integrated into a test set; Establishing a replacement judgment model, evaluating the test set and each voice material through the replacement judgment model, and obtaining a test value set corresponding to each voice material; generating a corresponding test vector according to the test value set; According to the formula Calculate the corresponding reuse value; Where: FY is the reuse value; e is the natural constant; PU is the test vector; K is the number of simulated data in the test set; The expression of the replacement judgment model is: ； Where: s is the voice material and simulation data; the output data is the replacement judgment value 1 or 0; Methods for comparing the priority of two voice materials include: Marking two voice materials that need to be compared in priority as first data and second data respectively; Setting up the formula and ; Where: b1 and b2 are both proportionality coefficients, and the value ranges are 0 < b1 ≤ 1, 0 < b2 ≤ 1; QY1 and QY2 are the first and second priority comparison values corresponding to the first and second data respectively; FY1 and FY2 are the multiplexing values corresponding to the first and second data respectively; CZ1 and CZ2 are the storage values corresponding to the first and second data respectively. When QY1 > QY2, the first data takes precedence over the second data. When QY1 < QY2, the second data takes precedence over the first data. When QY1 = QY2, the first data and the second data have the same priority.

2. A wearable device sports voice broadcasting method according to claim 1, characterized in that: Automatically adjust the voice parameters of the voice broadcast. The method includes: Obtain each audio data and establish an equivalent judgment model. Perform pairwise equivalent analysis on each audio data through the equivalent judgment model to obtain the equivalent judgment values between each audio data, and merge each audio data according to the equivalent judgment values to obtain each representative parameter and the application scenario corresponding to each representative parameter. Obtain the user's heart rate data in real time and determine the corresponding application scenario according to the heart rate data. Determine the corresponding representative parameter according to the application scenario; perform corresponding voice broadcast adjustment according to the representative parameter.

3. A wearable device sports voice broadcasting method according to claim 2, characterized in that: The expression of the equivalent judgment model is: ； Where: q corresponds to two audio data for comparison; the output data is the equivalent judgment value 1 or 0.

4. A wearable device sports voice broadcasting method according to claim 2, characterized in that: The method of merging each audio data according to the equivalent judgment value includes: Merge the audio data with the equivalent judgment value of 0 to obtain each initial classification; mark the voice parameters corresponding to the audio data with the highest share ratio in the initial classification as the initial parameters. Identify the share ratio of each initial classification and set the background value corresponding to each initial classification. Calculate the classification value of each initial classification according to the formula PV = FE × BY. Where: PV is the classification value; FE is the share ratio; BY is the classification value. Mark the initial classification with the classification value lower than the threshold X1 as the intermediate classification, and mark the initial classification with the classification value not lower than the threshold X1 as the merged classification. Determine the merged classification with the smallest difference from the intermediate classification according to the initial parameters corresponding to the intermediate classification and each merged classification; merge the intermediate classification into the merged classification with the smallest difference to obtain a new merged classification. Mark the initial parameters in the merged classification as the representative parameters.

Images