Schedule reminder method, device and electronic device based on neck massager
By obtaining the schedule text and extracting the triple word segmentation set, and determining the prompt level based on the keyword database, the problem of indistinguishable schedule reminders in the existing technology is solved, and a more efficient schedule reminder effect is achieved.
Patent Information
- Application Number
- CN202010380233.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-05-08
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2040-05-08
AI Technical Summary
The existing schedule reminder methods cannot distinguish reminders based on the importance of the schedule, resulting in poor reminders.
By obtaining the scheduled text, extracting the subject and triple word participle, determining the prompt level based on the number of keywords in the keyword database, and performing massage tasks according to different levels on the neck massager to achieve differentiated reminders of the schedule.
It improves the effectiveness and efficiency of schedule reminders, and can distinguish reminders based on the importance of the schedule, improving the user's reminder experience.
Smart Images

Figure CN113627866B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of neck massagers, and in particular to a schedule reminder method, device and electronic equipment based on a neck massager. Background Art
[0002] As the pace of life accelerates, more and more people are starting to plan their schedules. Currently, this is mainly done by recording the schedule in a memo, then setting an alarm in advance according to the schedule time, and using the alarm to ring to remind the schedule. However, this method cannot differentiate reminders based on the importance of the schedule, resulting in poor results for schedule reminders. Summary of the invention
[0003] Based on this, it is necessary to provide a schedule reminder method, device and electronic device based on a neck massager that can improve the efficiency of schedule reminders in response to the above technical problems.
[0004] A schedule reminder method based on a neck massager, the method comprising:
[0005] Get the schedule text and keyword library;
[0006] Determine all subjects in the schedule text;
[0007] Based on all the subjects, extracting the triple component word set and the prompt time in the schedule plan text;
[0008] Determining a prompt level according to the number of keywords in the keyword library included in the triple component word set;
[0009] Generate a corresponding schedule reminder task based on the reminder time, reminder level and schedule plan text;
[0010] The schedule reminder task is sent to the neck massager, so that the neck massager executes the schedule reminder task according to the reminder level when the reminder time arrives.
[0011] In one embodiment, obtaining the schedule text includes:
[0012] When a screenshot or copy operation occurs, obtain the conversation content in the instant messaging software pointed to by the screenshot or copy operation;
[0013] Transfer the conversation content from the instant messaging software to the preset target software based on drag and drop or paste operations;
[0014] When the session content in the target software is of a picture type, identifying text information in the session content;
[0015] A schedule text is generated according to the text information.
[0016] In one embodiment, determining all subjects in the schedule text includes:
[0017] Extracting at least one subject from the schedule text based on a pre-trained information extraction model;
[0018] The extracting of the set of triple components in the schedule text based on the subject includes:
[0019] Reconstructing the schedule text based on each extracted subject to obtain one or more reconstructed texts;
[0020] Extracting character features of the reconstructed text;
[0021] According to the character features, the relative predicate and the object of the corresponding subject are extracted from each reconstructed text, and the subject, the relative predicate and the object are combined to obtain a set of triple word components.
[0022] A schedule reminder method based on a neck massager, the method comprising:
[0023] Receive the schedule reminder task sent by the terminal;
[0024] Extracting a reminder time and a reminder level from the schedule reminder task;
[0025] When the prompt time is reached, determining a target massage mode corresponding to the prompt level;
[0026] The massage parameters are adjusted accordingly based on the target massage method, so that the user can be notified of the schedule reminder according to the target massage method.
[0027] In one embodiment, when the prompt time is reached, determining the target massage mode corresponding to the prompt level includes:
[0028] When the time participle does not contain a numeric character, converting the time participle into a complete standard time;
[0029] When the time participle contains a numeric character, converting the time participle into an incomplete standard time;
[0030] Combining the complete standard time and the incomplete standard time according to a preset time format to obtain a combined standard time;
[0031] When the combined standard time is reached, a target massage mode corresponding to the prompt level is determined.
[0032] In one embodiment, adjusting massage parameters based on the target massage method includes:
[0033] Obtain skin feature information;
[0034] Determining an optional range of standard massage parameters according to the skin characteristic information;
[0035] Determining whether the massage parameters corresponding to the target massage method are within an optional range;
[0036] If not, the massage parameters corresponding to the target massage method are adjusted accordingly based on the optional range.
[0037] In one embodiment, the optional range of determining the standard massage parameters according to the skin feature information includes:
[0038] Obtain standard skin dryness, standard skin smoothness, standard skin elasticity and standard massage parameters;
[0039] Determining a dryness deviation between the skin dryness and the standard skin dryness, a smoothness deviation between the skin smoothness and the standard skin smoothness, and an elasticity deviation between the skin elasticity and the standard skin elasticity;
[0040] Determining adjustment factors corresponding to the dryness deviation, smoothness deviation, and elasticity deviation;
[0041] The selectable range of the standard massage parameter is adjusted based on the adjustment factor.
[0042] A schedule reminder device based on a neck massager, the device comprising:
[0043] The prompt time generation module is used to obtain a schedule text and a keyword library; determine all subjects in the schedule text; and extract a triple component word set and a prompt time in the schedule text based on all subjects;
[0044] A prompt level generating module, used for determining a prompt level according to the number of keywords in the keyword library included in the triple component word set;
[0045] The reminder task generation module is used to generate a corresponding schedule reminder task based on the reminder time, reminder level and schedule plan text; the schedule reminder task is sent to the neck massager so that the neck massager executes the schedule reminder task according to the reminder level when the reminder time is reached.
[0046] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0047] Get the schedule text and keyword library;
[0048] Determine all subjects in the schedule text;
[0049] Based on the subject, extracting a set of triple components and a prompt time in the schedule text;
[0050] Determining a prompt level according to the number of keywords in the keyword library included in the triple component word set;
[0051] Generate a corresponding schedule reminder task based on the reminder time, reminder level and schedule plan text;
[0052] The schedule reminder task is sent to the neck massager, so that the neck massager executes the schedule reminder task according to the reminder level when the reminder time arrives.
[0053] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:
[0054] Get the schedule text and keyword library;
[0055] Determine all subjects in the schedule text;
[0056] Based on all the subjects, extracting the triple component word set and the prompt time in the schedule plan text;
[0057] Determining a prompt level according to the number of keywords in the keyword library included in the triple component word set;
[0058] Generate a corresponding schedule reminder task based on the reminder time, reminder level and schedule plan text;
[0059] The schedule reminder task is sent to the neck massager, so that the neck massager executes the schedule reminder task according to the reminder level when the reminder time arrives.
[0060] The above-mentioned schedule reminder method, device and electronic device based on the neck massager can extract all subjects in the schedule text by acquiring the schedule text, so that all triple word sets in the schedule text can be extracted based on all the extracted subjects; by generating one or more triple word sets, the corresponding prompt time and prompt level can be determined based on the generated triple word sets, so that the schedule reminder task can be generated based on the prompt time and prompt level, so that the neck massager that receives the schedule reminder task can make a schedule reminder according to the prompt level. Since the schedule reminder task can be automatically generated and the importance of the schedule can be determined based on the number of keywords in the schedule text, compared with the traditional schedule reminder based on the alarm clock, the present application can distinguish reminders according to the importance of the schedule, thereby improving the effect of the schedule reminder.
[0061] In addition, since this application only needs to obtain the schedule plan text to automatically generate a schedule reminder task, compared with the traditional method of recording schedules in a memo, this application can improve the efficiency of schedule reminders. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] Figure 1 A diagram of an application environment of a schedule reminder method based on a neck massager in one embodiment;
[0063] Figure 2 A schematic diagram of a flow chart of a schedule reminder method based on a neck massager in one embodiment;
[0064] Figure 3 A schematic diagram of a flow chart of steps for executing a schedule reminder task in one embodiment;
[0065] Figure 4 is a structural block diagram of a schedule reminder device based on a neck massager in one embodiment;
[0066] Figure 5 is a structural block diagram of a schedule reminder device based on a neck massager in another embodiment;
[0067] Figure 6 FIG. 4 is a diagram showing the internal structure of an electronic device in one embodiment. DETAILED DESCRIPTION
[0068] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0069] The schedule reminder method based on the neck massager provided in this application can be applied to Figure 1In the application environment shown. The terminal 102 communicates with the neck massager 104 through a network. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The terminal 102 runs a target application software that matches the neck massager 104, which is used to generate a schedule reminder task and send the generated schedule reminder task to the neck massager 104. When the corresponding reminder time arrives, the neck massager 104 executes the schedule reminder task by increasing the massage intensity and the like.
[0070] In one embodiment, Figure 2 As shown, a schedule reminder method based on a neck massager is provided, and the method is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:
[0071] S202, obtaining a schedule text and a keyword library.
[0072] The schedule text refers to the text information stored in text format for planning the trip. The schedule text can be a complete sentence or a paragraph of text composed of multiple short sentences. For example, "Let's discuss the recent new project in the small conference room at around 10 am tomorrow", or "Hello everyone, let's discuss the recent new project in the small conference room at around 10 am tomorrow. Please bring your report PPT (presentation software, Microsoft Office PowerPoint)". The keyword library refers to a word library set that pre-stores multiple keywords associated with the schedule. Based on this word library set, the importance of the schedule text can be determined.
[0073] Specifically, a target software matching the neck massager is running in the terminal. The user can directly input the schedule text in the target software, or input the picture or voice into the target software, and the target software recognizes the picture or voice to obtain the schedule text. Among them, the neck massager refers to an electronic instrument worn on the user's neck for improving the blood circulation in the neck. The server and the terminal both pre-store a keyword library and the version number of the keyword library. After the keyword library in the server is updated, the server can also update the version number of the keyword library accordingly, generate an update instruction according to the latest version number and the storage address of the keyword library, and send the update instruction to the terminal. The terminal extracts the latest version number in the update instruction, compares the latest version number with the version number of the pre-stored keyword library, and if they are inconsistent, the terminal downloads the latest version of the keyword library according to the storage address in the update instruction.
[0074] In one embodiment, multiple schedule texts within a period of time can be obtained, and each schedule text is input into the information extraction model respectively, and the information extraction model extracts all the triple word sets in each schedule text to obtain a triple set. Among them, the triple word set refers to generalizing the relational segmentation in the schedule text into the relational predicate, generalizing the entity into the subject and the object, and generating a segmentation set based on the generalized relational predicate, object and subject. For example, the triple word set can be <subject, relational predicate, object>. Entity refers to something that is distinguishable and exists independently in the real world, such as: a person's name, a place name, an object name, etc.
[0075] The terminal counts the frequency of each word in the triple set, and uses the word with a frequency higher than the preset threshold as a keyword. For example, when the two schedule texts are "Let's discuss the recent new project in the small conference room around 10 o'clock tomorrow, please bring your PPT" and "Let's make a PPT report at 3 o'clock tomorrow afternoon", the information extraction model extracts the triple word set <everyone, discuss, new project> and <everyone, bring, PPT> from the first schedule text, and extracts the triple word set <everyone, report, PPT> from the second conversation content. The terminal performs statistical analysis on these three triple word sets, thereby determining that the keywords are everyone and PPT. By extracting all triple word sets in each schedule text, representative word segments in the schedule text can be determined based on the triple word sets; by counting the word segments in multiple triple word sets, the word segments with a frequency higher than the preset threshold can be used as keywords, so that the schedule that the user needs to handle frequently can be determined based on the keywords, and the schedule that the user needs to handle frequently can be determined as an important schedule.
[0076] S204, determining all subjects in the schedule text.
[0077] Specifically, the terminal stores a pre-trained information extraction model. Among them, the information extraction model is a machine learning model that can analyze natural language at the vocabulary level and sentence level. For example, the information extraction model can perform word segmentation and part-of-speech recognition on natural language. When receiving the schedule text, the information extraction model determines whether there are commas or semicolons and other positive and negative signs with segmentation semantics in the schedule text. If so, the information extraction model segments the schedule text based on commas or semicolons and other positive and negative signs with segmentation semantics to obtain multiple short sentences. For example, when the schedule text is "Let's discuss this recent new project in the small conference room around 10 o'clock tomorrow, please bring your PPT", the short sentences obtained by segmentation are "Let's discuss this recent new project in the small conference room around 10 o'clock tomorrow" and "Please bring your PPT".
[0078] The information extraction model segments the short sentence to obtain characters in units of, for example, an English word or a Chinese character. The information extraction model extracts features for each character based on the semantic association before each character to obtain the first character features, and matches the first character features of each extracted character with the pre-stored subject features, so as to calculate the probability that the corresponding character is the subject based on the matching result. The information extraction model determines the target characters that make up the subject for the characters with probability values greater than the threshold, and determines the position information of the target characters in the short sentence. Based on the position information, adjacent target characters are determined as a subject. In this way, the information extraction model traverses each short sentence in the schedule text until the subject in each short sentence is extracted.
[0079] For example, in the above example, when the short sentence is "Let's discuss the latest new project in the small meeting room at about 10 o'clock tomorrow", the information extraction model determines that the two characters "大" and "家" are the target characters that make up the subject based on the first character features. Since "大" and "家" are adjacent characters, "大" and "家" can be combined to obtain the subject "大家".
[0080] In one embodiment, when adjacent target characters are determined as a subject based on the position information, the terminal matches the extracted subject with each subject in the preset subject set, and verifies whether the boundary of the extracted subject conforms to the word segmentation boundary based on the matching result. When it does not conform to the word segmentation boundary, the terminal extracts the target subject with the highest matching degree in the subject set, and re-segments the boundary of the extracted subject based on the target subject. By confirming the segmentation boundary of the extracted subject before determining the subject in the target text, the accuracy of subject extraction can be greatly improved.
[0081] In one embodiment, the information extraction model determines the space positions in the short sentence, and uses each space as a delimiter to segment the short sentence, so as to obtain multiple characters.
[0082] S206. Based on all the subjects, extract the three-element word segmentation set and the prompt time in the schedule text.
[0083] Specifically, the information extraction model determines whether the subject is extracted for each short sentence. If not, the information extraction model determines the arrangement order of each short sentence in the schedule text, as well as the position information of the incomplete short sentence from which the subject is not extracted. Based on the arrangement order and the position information, the complete short sentence before the incomplete short sentence is determined, and the incomplete short sentence is completed based on the subject in the complete short sentence. For the sake of description, this application refers to the short sentences from which the subject is not extracted as incomplete short sentences, and the short sentences from which the subject is extracted as complete short sentences. For example, "Please bring your PPT" can be completed based on the "everyone" in "Let's discuss this new project in the small conference room around 10 o'clock tomorrow" to obtain "Everyone please bring your PPT".
[0084] Furthermore, the information extraction task includes a subject extraction subtask, and a relational predicate and object extraction subtask. After obtaining the complete short sentence, the information extraction model inputs the complete short sentence into the relational predicate and object extraction subtask, and the relational predicate and object extraction subtask generate the second character feature of each character in the complete short sentence. A relational predicate set is pre-stored in the terminal. Among them, the relational predicate set refers to a set containing multiple predicates. The relational predicate and object extraction subtask binds the subject in the complete short sentence with each predicate in the relational set to obtain a relational subject set, and calculates the probability that the corresponding character is the object corresponding to each relational subject in the relational subject set based on the second character feature of each extracted character. The information extraction model determines the characters with probability values greater than the threshold as objects corresponding to the relational subjects. For example, when the relational predicate set includes "carry", the relational predicate and object extraction subtask determines the probability that each character in "Please carry your PPT" is the object of "Please carry your PPT", and determines the corresponding object as "PPT" based on the probability value.
[0085] Furthermore, the information extraction model performs word segmentation on the schedule text, deletes each word in the triple word set from the schedule text, and extracts word carrying numeric characters or time word with time semantic information from the remaining word. For example, "tomorrow" and "10 o'clock" are extracted from "tomorrow", "10 o'clock", "around", "in", "small conference room", "recently", "this", and "bar". After that, the extracted time word segmentations are combined according to the position information of each character in the schedule text to obtain the prompt time "tomorrow 10 o'clock".
[0086] In one embodiment, the second character feature introduces semantic information, because when a character is converted into a second character feature, semantic information is understood based on the characters near this character, thereby giving it the second character feature. Character features of semantically similar characters are close to each other in the vector space because the words near them are similar. For example, the comprehensive features composed of the character features of "carry", "wear", and "piggyback" are close to each other in the vector space, so the information extraction model can determine whether there are participles in the schedule text that are semantically similar to the predicates in the relational predicate set. When there are participles with similar semantics, the participles with similar semantics are bound to the subject to obtain the relational subject.
[0087] S208, determining a prompt level according to the number of keywords in the keyword library included in the triple word set.
[0088] Specifically, the terminal determines the number of keywords in the one or more triplet word sets extracted from the schedule text, and determines the corresponding prompt level according to the number. For example, when the number exceeds the preset number threshold, the corresponding prompt level can be set to a high level. For another example, the terminal subtracts the preset number threshold from the number of keywords contained in the schedule text to obtain the number difference. The terminal pre-stores the correspondence between the number difference and the prompt level. Based on this correspondence, the terminal can determine the prompt level corresponding to the number difference. The correspondence between the number difference and the prompt level can be: when the number difference is less than 0, the corresponding prompt level is level 1, and the corresponding massage method is that the massager massages with a light massage force; when the number difference is less than 2 and greater than 0, the corresponding prompt level is level 2, and the corresponding massage method is that the massager massages with a heavy massage force; when the number value is greater than or equal to 2, the prompt level is level 2, the corresponding prompt level is level 3, and the corresponding massage method is that the massager massages with a heavy massage force, and turns on the hot compress function. Note that this example is only for the convenience of readers to understand this solution more clearly, and the actual meaning of the example value can be ignored.
[0089] In one embodiment, the keywords in the keyword library can be called basic keywords, and one or more keywords added based on the basic keywords can be called subordinate keywords. It should be noted that when the terminal counts the number of keywords contained in the triple word set, the subordinate keywords and their corresponding basic keywords are equivalent. That is to say, if one or more triple word sets contain a basic keyword and a corresponding subordinate keyword at the same time, or only contain a subordinate keyword corresponding to a basic keyword, the terminal finally counts the corresponding basic keywords contained in the triple word set, so that the final statistical result of the terminal is which basic keywords are contained in one or more triple word sets. For example, the terminal adds keywords A1 and A2 that are synonymous with A. If the basic keyword A appears twice, the subordinate keyword A2 appears twice, and the basic keyword B appears once in multiple triple word sets, then the number of keywords contained in the petition information is still 2 in the final statistics: A and B. By adding subordinate keywords, the synonymous participles in multiple triple word sets can be merged, thereby reducing the probability of inaccurate prompt levels due to counting too many synonymous participles.
[0090] S210, generating a corresponding schedule reminder task based on the reminder time, reminder level and schedule plan text.
[0091] S212, sending the schedule reminder task to the neck massager, so that the neck massager executes the schedule reminder task according to the reminder level when the reminder time arrives.
[0092] Specifically, the terminal generates a schedule reminder task according to the reminder time, reminder level and schedule plan text, and sends the schedule reminder task to the matching neck massager based on the target software, and the matching neck massager executes the schedule reminder task.
[0093] In one embodiment, since users generally like to be reminded of their schedules some time in advance, the advance time can be pre-stored in the terminal. When the reminder time is determined, the terminal updates the reminder time according to the advance time, obtains the updated reminder time, and generates a schedule reminder task according to the updated reminder time.
[0094] In one embodiment, when the sending fails because the neck massager is not turned on, the terminal will cache the schedule reminder task that failed to be sent, and when the neck massager is turned on, send the schedule reminder task whose reminder time does not exceed the current time to the neck massager.
[0095] In the schedule reminder method of the neck massager,
[0096] By acquiring the schedule text, all subjects in the schedule text can be extracted, and then all triple word sets in the schedule text can be extracted based on all extracted subjects; by generating one or more triple word sets, the corresponding reminder time and reminder level can be determined based on the generated triple word sets, and then a schedule reminder task can be generated based on the reminder time and reminder level, so that the neck massager that receives the schedule reminder task can make a schedule reminder according to the prompt level. Since the schedule reminder task can be automatically generated and the importance of the schedule can be determined based on the number of keywords in the schedule text, compared with the traditional schedule reminder based on the alarm clock, the present application can distinguish reminders according to the importance of the schedule, thereby improving the effect of the schedule reminder.
[0097] In addition, since this application only needs to obtain the schedule plan text to automatically generate a schedule reminder task, compared with the traditional method of recording schedules in a memo, this application can improve the efficiency of schedule reminders.
[0098] In one embodiment, obtaining the schedule text includes: when a screenshot or copy operation occurs, obtaining the conversation content located in the instant messaging software pointed to by the screenshot or copy operation; based on a drag or paste operation, transferring the conversation content from the instant messaging software to a preset target software; when the conversation content located in the target software is of a picture type, identifying the text information in the conversation content; and generating the schedule text based on the text information.
[0099] Specifically, the terminal can simultaneously run an instant messaging software and a target software, wherein the instant messaging software can be WeChat, email, etc. When a user conducts a conversation based on the instant messaging software, the user can copy or screenshot the conversation content in the instant messaging software, and then transfer the conversation content to the target software by pasting, dragging, etc. The target software determines the content type of the conversation content obtained by dragging, pasting, etc. If it is a text type, the target software directly displays the conversation content in the corresponding display window; if it is a picture type, the target software identifies the text information in the picture and displays the text information in the display window. The user can modify the conversation content in the display window at will. The target software monitors the user's confirmation operation. When the user clicks the confirmation control, or within the preset time from displaying the conversation content, the user's confirmation information is still not obtained, the target software uses the conversation content in the display window as the final conversation content. At the same time, the terminal generates a schedule text based on the text information in the conversation content.
[0100] In this embodiment, the schedule text can be generated through simple operations such as screenshots, copying, dragging, and pasting. Compared with the traditional method of manually entering the schedule in the memo, this application can improve the efficiency of generating the schedule text, thereby improving the reminder efficiency of the schedule.
[0101] In one embodiment, determining all subject participles in a schedule text includes: extracting at least one subject from the schedule text based on a pre-trained information extraction model; reconstructing the schedule text based on each extracted subject to obtain one or more reconstructed texts; extracting character features of the reconstructed texts; and extracting a relative predicate and an object of the corresponding subject from each reconstructed text based on the character features, combining the subject, the relative predicate and the object to obtain a set of triplet word groups.
[0102] The multiple reconstructed texts refer to at least two reconstructed texts.
[0103] Specifically, after extracting at least one subject from the schedule text based on the pre-trained information extraction model, the information extraction model adds the extracted subject to the preset position in the corresponding short sentence, thereby obtaining a reconstructed text. For example, when the short sentence is "Everyone will discuss the recent new project in the small conference room around 10 am tomorrow" and the subject is "everyone", the subject can be added before the first character of the corresponding short sentence based on the preset separator "|", and the reconstructed text "Everyone|Everyone will discuss the recent new project in the small conference room around 10 am tomorrow" can be obtained. Afterwards, the information extraction model determines the second character feature of each character based on the subject before the separator, and determines the relative predicate and object corresponding to the subject based on the second character feature, and generates a trigram word set based on the subject, the relative predicate and the object.
[0104] In this embodiment, since the subject in the short sentence is divided by a separator, the information extraction model can quickly determine the subject participle in the short sentence based on the separator, so that the second character feature of each character can be quickly generated based on the subject participle.
[0105] In one embodiment, Figure 3 As shown, a schedule reminder method based on a neck massager is provided, and the method is applied to Figure 1 Take the neck massager in the figure as an example to illustrate, including the following steps:
[0106] S302: receiving a schedule reminder task sent by a terminal.
[0107] S304: extracting the reminder time and reminder level from the schedule reminder task.
[0108] S306: When the prompt time arrives, determine the target massage method corresponding to the prompt level.
[0109] S308, adjusting massage parameters accordingly based on the target massage method, so that the user can obtain a schedule reminder according to the target massage method.
[0110] Specifically, after the neck massager receives the schedule reminder task sent by the terminal, the neck massager extracts the reminder time and the reminder level from the schedule reminder task, and determines the corresponding target massage method according to the extracted reminder level. More specifically, the neck massager pre-stores the correspondence between the reminder level and the massage method. After determining the reminder level, the corresponding target massage method can be determined based on the correspondence, and when the reminder time is reached, the current massage parameters are adjusted according to the massage parameters in the target massage method. For example, a low-level target massage method can be a gentle massage, and a high-level target massage method can be a strong massage.
[0111] In one of the embodiments, when the reminder time arrives, the terminal determines whether the neck massager is turned on. If not, the terminal can push the schedule on the screen or voice broadcast the schedule text.
[0112] In one embodiment, the neck massager has an acceleration sensor. When the reminder time arrives, the neck massager obtains the motion data collected by the acceleration sensor, and determines the frequency domain characteristics and time domain characteristics of the motion data, and determines whether the user is in a state of intense exercise, for example, whether the user is running, based on the frequency domain characteristics and the time domain characteristics. If in a state of intense exercise, the neck massager returns the schedule reminder task to the terminal, and the terminal executes the schedule reminder task. Since the human body may not feel the change in massage method during intense exercise, auxiliary reminders through the terminal help improve the effectiveness of schedule reminders.
[0113] In one of the embodiments, the user can customize the massage method in the target software, so that when the reminder time arrives, the neck massager can massage according to the user-defined massage method.
[0114] In this embodiment, since most of the current schedule reminders are in the form of setting alarms, which are not highly correlated with what the user is actually doing at the moment, the reminder effect is usually not good and is easily ignored by the user. Therefore, using a neck massager to remind the user of their schedule can not only improve the efficiency of schedule reminders, but also improve the effect of schedule reminders because it is highly correlated with what the user is actually doing at the moment.
[0115] In one embodiment, the prompt time includes at least one time participle; when the time participle does not include a numerical character, the time participle is converted into a complete standard time; when the time participle includes a numerical character, the time participle is converted into an incomplete standard time; according to a preset time format, the complete standard time and the incomplete standard time are combined to obtain a combined standard time; when the combined standard time is reached, a target massage method corresponding to the prompt level is determined.
[0116] Among them, the complete standard time refers to the time in the standard world time format composed of year, month, day, hour, minute and second; the incomplete standard time refers to the time in the standard world time format composed of hour, minute and second. The preset time format refers to the standard world time format. The time participle refers to the participle required to form the prompt time. For example, when the prompt time is "tomorrow at 10 o'clock", the corresponding time participle is "tomorrow" and "10 o'clock".
[0117] Specifically, after obtaining the time participle, the neck massager determines whether the current time participle contains numeric characters. If it does not contain numeric characters, the neck massager converts the time participle into a complete standard time in the standard world time format composed of year, month, day, hour, minute, and second according to the first mapping relationship in the preset first mapping relationship set. For example, when the time participle is "tomorrow", the corresponding first mapping relationship is "get the current year, month, and day at midnight (2020-01-02 00:00:00), and add one day to the current year, month, and day (2020-01-03 00:00:00)". Among them, the first mapping set contains conversion rules for time participles that do not contain numeric characters, such as "tomorrow", "afternoon", and "evening".
[0118] When the current time segment contains a numerical character, the neck massager converts the time segment into an incomplete standard time in a standard world time format composed of hours, minutes and seconds according to the second mapping relationship in the preset second mapping relationship set. Among them, the second mapping set contains conversion rules for time segment containing numerical characters such as "S% o'clock", "S% hours", "S% minutes", "S% half past one", etc. S% is a formal parameter of a specific time character. For example, when the time segment is "10 o'clock", the neck massager determines that the moment corresponding to "point" is "hour". At this time, the neck massager determines the corresponding second mapping relationship according to "point", and generates the incomplete standard time based on the corresponding second mapping relationship. The specific steps of generating the incomplete standard time can be: determine the character order of each character in "00:00:00", and determine the character before the first appearance of ":" based on the character order, and then replace the character before the first appearance of ":" with the value "10" to obtain the incomplete standard time "10:00:00". The neck massager combines the complete standard time and the incomplete standard time according to the preset time format to obtain the combined standard time, and determines the time when the massage parameters need to be adjusted according to the combined standard time. For example, "2020-01-03 00:00:00" and "10:00:00" are combined to obtain "2020-01-03 10:00:00".
[0119] In this embodiment, by converting the ambiguous reminder time into an accurate combined standard time in a standard world time format, the user can be effectively reminded of the schedule according to the combined standard time.
[0120] In one embodiment, adjusting massage parameters based on a target massage method includes: acquiring skin feature information; determining a range of standard massage parameters based on the skin feature information; determining whether the massage parameters corresponding to the target massage method are within the range; if not, adjusting the massage parameters corresponding to the target massage method based on the range.
[0121] Among them, skin characteristic information includes skin dryness, skin elasticity, skin smoothness, skin inflammation and other information.
[0122] Specifically, the neck massager is embedded with different types of sensors, such as moisture measurement sensors, pressure sensors, etc., which detect the moisture, oil and elasticity of the user's skin through various sensors, and determine the skin characteristic information based on the detected moisture, oil and elasticity. For example, when the skin characteristic information is skin dryness, the way to obtain skin dryness is: due to the fluidity of water in skin cells, the moisture measurement sensor can be automatically controlled to perform multi-vector repeated detection, and a large amount of data collected by the sensor can be analyzed through a preset algorithm to give the data closest to the actual situation, just like a person swimming in a swimming pool with water and oil, different water and oil content swim at different speeds, thereby detecting the water and oil content. Among them, skin water and oil data refers to information such as the water content and oil content of the skin. There are multiple levels of skin dryness, and a combination of water content and oil content corresponds to a skin dryness level. For another example, when the skin characteristic information is skin elasticity, pressure can be applied to the skin, and the skin elasticity can be calculated based on the pressure sensor.
[0123] Furthermore, the neck massager pre-stores a mapping relationship between skin feature information and the range of standard massage parameters. After the user's skin feature information is determined, the range of standard massage parameters corresponding to the skin feature information can be queried based on the mapping relationship. The neck massager determines whether the massage parameters corresponding to the target massage method are within the range. If not, the neck massager adjusts the massage parameters of the target massage method accordingly so that the massage parameters of the target massage method are within the range, and adjusts the massage method based on the massage parameters within the range. For example, when the massage frequency corresponding to the target massage method is out of the range, the massage frequency is correspondingly reduced so that the massage frequency is within the range.
[0124] In this embodiment, since different users have different skin characteristic information, they can withstand different massage methods. For example, when the user's skin is relatively dry, a high-intensity massage method may damage the user's skin, thereby reducing the user experience. Therefore, the target massage method is adjusted according to the user's skin characteristic information to make the massage method more targeted.
[0125] In one embodiment, determining the range of standard massage parameters based on skin characteristic information includes: obtaining standard skin dryness, standard skin smoothness, standard skin elasticity and standard massage parameters; determining the dryness deviation between skin dryness and standard skin dryness, the smoothness deviation between skin smoothness and the standard skin smoothness, and the elasticity deviation between skin elasticity and standard skin elasticity; determining adjustment factors corresponding to the dryness deviation, smoothness deviation and elasticity deviation; and adjusting the range of standard massage parameters based on the adjustment factors.
[0126] Among them, the massage parameters include parameter factors such as pulse frequency, hot compress temperature, and massage intensity. Different parameter factors correspond to different parameter adjustment ranges. For example, when the parameter factor is hot compress temperature, the corresponding range may be 38 degrees Celsius to 42 degrees Celsius. Standard skin dryness, standard skin smoothness, and standard skin elasticity refer to the skin dryness, skin smoothness, and skin elasticity obtained by averaging the skin feature information of a large number of users with healthy skin.
[0127] Specifically, the neck massager pre-stores standard massage parameters corresponding to standard skin dryness, standard skin smoothness, and standard skin elasticity. Since the drier the skin, the worse the user's skin condition; the smoother the skin and the higher the elasticity, the healthier the user's skin quality. Therefore, after obtaining the standard massage parameters, the neck massager will subtract the standard skin dryness from the skin dryness monitored by the sensor to obtain a dryness deviation with positive and negative signs; and subtract the corresponding skin smoothness and skin elasticity monitored by the sensor from the standard skin smoothness and standard skin elasticity to obtain a smoothness deviation and elasticity deviation with positive and negative signs.
[0128] Furthermore, the neck massager divides the dryness deviation, smoothness deviation, and elasticity deviation with positive and negative signs by the corresponding standard skin dryness, standard skin smoothness, and standard skin elasticity to obtain the dryness deviation percentage, smoothness deviation percentage, and elasticity deviation percentage, and weights and averages the dryness deviation percentage, smoothness deviation percentage, and elasticity deviation percentage to obtain the adjustment factor. For example, when the dryness deviation percentage is 1%, the smoothness deviation percentage is -1%, and the elasticity deviation percentage is 2%, and the corresponding weights are (1, 2, 1), the adjustment factor is: (1%*1-1%*2+2%*1)=1%. Afterwards, the neck massager determines whether the adjustment factor is positive or negative. When the adjustment factor is a positive number, the neck massager correspondingly increases the range of the standard massage parameters of the adjustment factor, for example, increases the range of the standard massage parameters by 1%; when the adjustment factor is a negative number, the neck massager correspondingly decreases the range of the standard massage parameters.
[0129] In one of the embodiments, when the range of the standard massage parameters is adjusted based on the adjustment factor, the neck massager determines whether the adjusted optional range exceeds the adjustment range supported by the instrument. If so, the neck massager corresponds to the range of the standard massage parameters so that it is within the range supported by the instrument.
[0130] In this embodiment, since the optional range of massage parameters is adjusted correspondingly based on skin smoothness, skin dryness and skin elasticity, the corresponding massage method is more in line with the user's skin characteristic information, thereby greatly improving the user experience.
[0131] It should be understood that although Figure 2 , 3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 , 3 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.
[0132] In one embodiment, Figure 4 As shown, a schedule reminder device 400 based on a neck massager is provided, comprising: a reminder time generation module 402, a reminder level generation module 404 and a reminder task generation module 406, wherein:
[0133] The prompt time generation module 402 is used to obtain the schedule text and the keyword library; determine all the subjects in the schedule text; and extract the triple component word set and the prompt time in the schedule text based on all the subjects.
[0134] The prompt level generating module 404 is used to determine the prompt level according to the number of keywords in the keyword library included in the triple word set.
[0135] The reminder task generation module 406 is used to generate a corresponding schedule reminder task based on the reminder time, reminder level and schedule plan text; and send the schedule reminder task to the neck massager so that the neck massager executes the schedule reminder task according to the reminder level when the reminder time arrives.
[0136] In one embodiment, the above-mentioned prompt time generation module 402 also includes a planned text acquisition module 4021, which is used to obtain the conversation content in the instant messaging software pointed to by the screenshot or copy operation when a screenshot or copy operation occurs; based on a drag or paste operation, transfer the conversation content from the instant messaging software to a preset target software; when the conversation content in the target software is of a picture type, identify the text information in the conversation content; and generate a schedule text based on the text information.
[0137] In one embodiment, the above-mentioned prompt time generation module 402 also includes a subject extraction module 4022, which is used to extract at least one subject from the schedule text based on a pre-trained information extraction model; reconstruct the schedule text based on each extracted subject to obtain one or more reconstructed texts; extract character features of the reconstructed text; based on the character features, extract the relative predicate and object of the corresponding subject from each reconstructed text, and combine the subject, the relative predicate and the object to obtain a set of triple components.
[0138] like Figure 5 As shown, a schedule reminder device 500 based on a neck massager is provided, comprising a receiving module 502, a massage mode determination module 504, and a parameter adjustment module 506, wherein:
[0139] The receiving module 502 is used to receive a schedule reminder task sent by a terminal.
[0140] The massage mode determination module 504 is used to extract the reminder time and the reminder level from the schedule reminder task; when the reminder time arrives, determine the target massage mode corresponding to the reminder level.
[0141] The parameter adjustment module 506 is used to adjust the massage parameters according to the target massage method, so that the user can get the schedule reminder according to the target massage method.
[0142] In one embodiment, the massage mode determination module 504 also includes a time conversion module 5041, which is used to convert the time participle into a complete standard time when the time participle does not contain a numerical character; when the time participle contains a numerical character, the time participle is converted into an incomplete standard time; according to a preset time format, the complete standard time and the incomplete standard time are combined to obtain a combined standard time; when the combined standard time is reached, a target massage mode corresponding to the prompt level is determined.
[0143] In one embodiment, the parameter adjustment module 506 also includes a skin feature information acquisition module 5061, which is used to obtain skin feature information; determine the range of standard massage parameters based on the skin feature information; determine whether the massage parameters corresponding to the target massage method are within the range; if not, adjust the massage parameters corresponding to the target massage method based on the range.
[0144] In one embodiment, the skin feature information acquisition module 5061 is also used to obtain standard skin dryness, standard skin smoothness, standard skin elasticity and standard massage parameters; determine the dryness deviation between the skin dryness and the standard skin dryness, the smoothness deviation between the skin smoothness and the standard skin smoothness, and the elasticity deviation between the skin elasticity and the standard skin elasticity; determine the adjustment factors corresponding to the dryness deviation, smoothness deviation and elasticity deviation; and adjust the range of the standard massage parameters based on the adjustment factors.
[0145] For the specific definition of the schedule reminder device based on the neck massager, please refer to the definition of the schedule reminder method based on the neck massager above, which will not be repeated here. Each module in the above-mentioned schedule reminder device based on the neck massager can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0146] In one embodiment, an electronic device is provided. The electronic device may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown. The electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a schedule reminder method based on a neck massager is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc.
[0147] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
[0148] In one embodiment, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0149] Get the schedule text and keyword library;
[0150] Identify all subjects in the schedule text;
[0151] Based on all subjects, extract the trigram word set and prompt time in the schedule text;
[0152] Determine the prompt level according to the number of keywords in the keyword library included in the triple component word set;
[0153] Generate a corresponding schedule reminder task based on the reminder time, reminder level and schedule plan text;
[0154] The schedule reminder task is sent to the neck massager, so that the neck massager executes the schedule reminder task according to the reminder level when the reminder time arrives.
[0155] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0156] When a screenshot or copy operation occurs, obtain the conversation content in the instant messaging software pointed to by the screenshot or copy operation;
[0157] Transfer the conversation content from the instant messaging software to the preset target software based on drag and drop or paste operations;
[0158] When the conversation content in the target software is of picture type, identifying text information in the conversation content;
[0159] Generate a schedule text based on text information.
[0160] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0161] Extracting at least one subject from the schedule text based on a pre-trained information extraction model;
[0162] Based on all subjects, the set of triples extracted from the schedule text includes:
[0163] Reconstructing the schedule text based on each extracted subject to obtain one or more reconstructed texts;
[0164] Extract character features of reconstructed text;
[0165] According to the character features, the relative predicate and the object of the corresponding subject are extracted from each reconstructed text, and the subject, the relative predicate and the object are combined to obtain a set of triple word components.
[0166] In one embodiment, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0167] Receive the schedule reminder task sent by the terminal;
[0168] Extract reminder time and reminder level from the schedule reminder task;
[0169] When the prompt time is reached, a target massage method corresponding to the prompt level is determined;
[0170] The massage parameters are adjusted accordingly based on the target massage method, so that the user can be notified of the schedule reminder according to the target massage method.
[0171] In one embodiment, the prompt time includes at least one time participle; when the processor executes the computer program, the following steps are also implemented:
[0172] When the time participle does not contain a numeric character, the time participle is converted to the complete standard time;
[0173] When a time participle contains a numeric character, the time participle is converted to incomplete standard time;
[0174] According to the preset time format, the complete standard time and the incomplete standard time are combined to obtain the combined standard time;
[0175] When the combined standard time is reached, a target massage mode corresponding to the prompt level is determined.
[0176] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0177] Obtain skin feature information;
[0178] Determine the range of standard massage parameters based on skin characteristic information;
[0179] Determining whether the massage parameters corresponding to the target massage method are within a range;
[0180] If not, the massage parameters corresponding to the target massage method are adjusted accordingly based on the selectable range.
[0181] In one embodiment, the skin characteristic information includes skin dryness, skin smoothness, and skin elasticity; when the processor executes the computer program, the following steps are also implemented:
[0182] Obtain standard skin dryness, standard skin smoothness, standard skin elasticity and standard massage parameters;
[0183] Determining the dryness deviation between skin dryness and standard skin dryness, the smoothness deviation between skin smoothness and standard skin smoothness, and the elasticity deviation between skin elasticity and standard skin elasticity;
[0184] Determine adjustment factors corresponding to dryness deviation, smoothness deviation, and elasticity deviation;
[0185] The range of the standard massage parameters is adjusted based on the adjustment factor.
[0186] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0187] Get the schedule text and keyword library;
[0188] Identify all subjects in the schedule text;
[0189] Based on the subject, extract the trigram word set and prompt time in the schedule text;
[0190] Determine the prompt level according to the number of keywords in the keyword library included in the triple component word set;
[0191] Generate a corresponding schedule reminder task based on the reminder time, reminder level and schedule plan text;
[0192] The schedule reminder task is sent to the neck massager, so that the neck massager executes the schedule reminder task according to the reminder level when the reminder time arrives.
[0193] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0194] When a screenshot or copy operation occurs, obtain the conversation content in the instant messaging software pointed to by the screenshot or copy operation;
[0195] Transfer the conversation content from the instant messaging software to the preset target software based on drag and drop or paste operations;
[0196] When the conversation content in the target software is of picture type, identifying text information in the conversation content;
[0197] Generate a schedule text based on text information.
[0198] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0199] Extracting at least one subject from the schedule text based on a pre-trained information extraction model;
[0200] Based on the subject, the set of triples extracted from the schedule text includes:
[0201] Reconstructing the schedule text based on each extracted subject to obtain one or more reconstructed texts;
[0202] Extract character features of reconstructed text;
[0203] According to the character features, the relative predicate and the object of the corresponding subject are extracted from each reconstructed text, and the subject, the relative predicate and the object are combined to obtain a set of triple word components.
[0204] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0205] Receive the schedule reminder task sent by the terminal;
[0206] Extract reminder time and reminder level from the schedule reminder task;
[0207] When the prompt time is reached, a target massage method corresponding to the prompt level is determined;
[0208] The massage parameters are adjusted accordingly based on the target massage method, so that the user can be notified of the schedule reminder according to the target massage method.
[0209] In one embodiment, the prompt time includes at least one time participle; when the computer program is executed by the processor, the following steps are also implemented:
[0210] When the time participle does not contain a numeric character, the time participle is converted to the complete standard time;
[0211] When a time participle contains a numeric character, the time participle is converted to incomplete standard time;
[0212] According to the preset time format, the complete standard time and the incomplete standard time are combined to obtain the combined standard time;
[0213] When the combined standard time is reached, a target massage mode corresponding to the prompt level is determined.
[0214] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0215] Obtain skin feature information;
[0216] Determine the range of standard massage parameters based on skin characteristic information;
[0217] Determining whether the massage parameters corresponding to the target massage method are within a range;
[0218] If not, the massage parameters corresponding to the target massage method are adjusted accordingly based on the selectable range.
[0219] In one embodiment, the skin characteristic information includes skin dryness, skin smoothness and skin elasticity; when the computer program is executed by the processor, the following steps are also implemented:
[0220] Obtain standard skin dryness, standard skin smoothness, standard skin elasticity and standard massage parameters;
[0221] Determining the dryness deviation between skin dryness and standard skin dryness, the smoothness deviation between skin smoothness and standard skin smoothness, and the elasticity deviation between skin elasticity and standard skin elasticity;
[0222] Determine adjustment factors corresponding to dryness deviation, smoothness deviation, and elasticity deviation;
[0223] The range of the standard massage parameters is adjusted based on the adjustment factor.
[0224] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0225] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0226] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
Claims
1. A schedule reminder method based on a neck massager, It is characterized in that The method comprises: Get the schedule text and keyword library; Determine all subjects in the schedule text; Reconstructing the schedule text based on each extracted subject to obtain a reconstructed text; Extracting character features of the reconstructed text; extracting the relational predicate and the object of the corresponding subject from each reconstructed text according to the character features, combining the subject, the relational predicate and the object to obtain a triad of word sets, wherein the triad of word sets is a set of word sets generated by generalizing the relational word sets in the schedule text into relational predicates, generalizing the entities into subjects and objects, and based on the generalized relational predicates, objects and subjects; Extracting time participles from the remaining participles in the schedule text except for the participles in the trigram participle set; Combining the time participles according to the position information of the characters in the schedule text to obtain a prompt time, wherein the prompt time includes at least one time participle; Determining a prompt level according to the number of keywords in the keyword library included in the triple component word set; Generate a corresponding schedule reminder task based on the reminder time, reminder level and schedule plan text; The schedule reminder task is sent to the neck massager, so that the neck massager executes the schedule reminder task according to the prompt level when the prompt time is reached, and converts the time participles that do not contain numerical characters and the time participles that contain numerical characters into complete standard time and incomplete standard time respectively, and combines the complete standard time and the incomplete standard time according to a preset time format to obtain a combined standard time; when the combined standard time is reached, determines the target massage method corresponding to the prompt level.
2. The method according to claim 1, It is characterized in that The obtaining of the schedule text includes: When a screenshot or copy operation occurs, obtain the conversation content in the instant messaging software pointed to by the screenshot or copy operation; Transfer the conversation content from the instant messaging software to the preset target software based on drag and drop or paste operations; When the session content in the target software is of a picture type, identifying text information in the session content; A schedule text is generated according to the text information.
3. The method according to claim 1, It is characterized in that Determining all subjects in the schedule text includes: At least one subject is extracted from the schedule text based on a pre-trained information extraction model.
4. A schedule reminder method based on a neck massager, It is characterized in that The method comprises: Receiving a schedule reminder task sent by a terminal, wherein the schedule reminder task is generated according to a reminder time, a reminder level, and a schedule plan text; Extracting the reminder time and the reminder level from the schedule reminder task; the reminder level is determined based on the number of keywords in the keyword library included in the trigram set; the trigram set is determined based on the reconstructed text, and the reconstructed text is obtained by reconstructing the schedule text based on each subject extracted from the schedule text; the reminder time is obtained by combining time participles according to the position information of the characters in the schedule text; the time participles are extracted from the remaining participles in the schedule text except the participles in the trigram set; The triplet word set is obtained by extracting the relational predicate and the object of the subject from each reconstructed text according to the extracted character features of the reconstructed text, combining the subject, the relational predicate and the object, generalizing the relational word segmentation in the schedule text into the relational predicate, generalizing the entity into the subject and the object, and generating a word segmentation set according to the generalized relational predicate, the object and the subject; When the time participle does not contain a numeric character, converting the time participle into a complete standard time; When the time participle contains a numeric character, converting the time participle into an incomplete standard time; Combining the complete standard time and the incomplete standard time according to a preset time format to obtain a combined standard time; When the combined standard time is reached, determining a target massage mode corresponding to the prompt level; The massage parameters are adjusted accordingly based on the target massage method, so that the user can be notified of the schedule reminder according to the target massage method.
5. The method according to claim 4, It is characterized in that The adjusting of massage parameters based on the target massage method includes: Obtain skin feature information; determining a range of standard massage parameters according to the skin characteristic information; Determining whether the massage parameters corresponding to the target massage method are within a range; If not, the massage parameters corresponding to the target massage method are adjusted accordingly based on the optional range.
6. The method according to claim 5, It is characterized in that The skin characteristic information includes skin dryness, skin smoothness and skin elasticity; the range of the standard massage parameters determined according to the skin characteristic information includes: Obtain standard skin dryness, standard skin smoothness, standard skin elasticity and standard massage parameters; determining a dryness deviation between the skin dryness and the standard skin dryness, a smoothness deviation between the skin smoothness and the standard skin smoothness, and an elasticity deviation between the skin elasticity and the standard skin elasticity; Determining adjustment factors corresponding to the dryness deviation, smoothness deviation, and elasticity deviation; The range of the standard massage parameters is adjusted based on the adjustment factor.
7. A schedule reminder device based on a neck massager, It is characterized in that The device comprises: The prompt time generation module is used to obtain a schedule text and a keyword library; determine all subjects in the schedule text; reconstruct the schedule text based on each extracted subject to obtain a reconstructed text; extract character features of the reconstructed text; extract the relative predicate and object of the corresponding subject from each reconstructed text according to the character features, combine the subject, the relative predicate and the object to obtain a triple word set, wherein the triple word set is a set of word sets generated by generalizing the relative word segments in the schedule text into relative predicates, generalizing entities into subjects and objects, and based on the generalized relative predicates, objects and subjects; extract time word segments from the remaining word segments in the schedule text except the word segments in the triple word set; combine the time word segments according to the position information of the characters in the schedule text to obtain a prompt time, wherein the prompt time contains at least one time word segment; A prompt level generating module, used for determining a prompt level according to the number of keywords in the keyword library included in the triple component word set; A reminder task generation module is used to generate a corresponding schedule reminder task based on the reminder time, the reminder level and the schedule plan text; send the schedule reminder task to the neck massager so that the neck massager executes the schedule reminder task according to the prompt level when the reminder time is reached, and converts the time participle that does not contain numerical characters and the time participle that contains numerical characters into a complete standard time and an incomplete standard time respectively, and combines the complete standard time and the incomplete standard time according to a preset time format to obtain a combined standard time; when the combined standard time is reached, determines a target massage method corresponding to the prompt level.
8. The device according to claim 7, It is characterized in that The schedule reminder device based on the neck massager also includes a schedule text acquisition module, which is used to obtain the conversation content in the instant messaging software pointed to by the screenshot or copy operation when a screenshot or copy operation occurs; based on a drag or paste operation, transfer the conversation content from the instant messaging software to a preset target software; when the conversation content in the target software is of a picture type, identify the text information in the conversation content; and generate a schedule text based on the text information.
9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
