Voice broadcast control method and device, electronic equipment and storage medium

Abstract

The invention provides a voice broadcast control method and device, electronic equipment and a storage medium, and belongs to the technical field of electronic equipment.The method comprises the steps that in response to a received first notification message, keywords in the first notification message are extracted; processing the first notification message based on the keyword to obtain a second notification message; and converting the second notification message into a voice message, and performing voice broadcast on the voice message. According to the voice broadcast control method and device, the electronic equipment and the storage medium provided by the invention, the efficiency of acquiring the notification message through the terminal by a user can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of electronic equipment, and more specifically, to a voice broadcast control method, device, electronic equipment and storage medium. Background Art

[0002] With the development of computer technology, various terminal devices such as smartphones and tablets are constantly launching new functions and services, covering various fields such as social, entertainment, work, study, and finance. The number of notification messages that users can obtain through terminal devices is also increasing. These notification messages come from a wide range of sources, such as various applications, social media platforms, email services, news information clients, etc. However, the huge amount of information can also cause a burden to users. Therefore, how to effectively improve the efficiency of users obtaining notification messages through terminals so that they can quickly filter out important information in a short time and avoid being disturbed by irrelevant messages has become a key issue that needs to be solved urgently. Summary of the invention

[0003] The purpose of the present disclosure is to provide a voice broadcast control method, device, electronic device and storage medium to improve the efficiency of users obtaining notification messages through a terminal.

[0004] According to a first aspect of the embodiments of the present disclosure, a voice broadcast control method is provided, comprising: In response to receiving a first notification message, extracting keywords in the first notification message; Processing the first notification message based on the keyword to obtain a second notification message; The second notification message is converted into a voice message, and the voice message is voice broadcasted.

[0005] A second aspect of the embodiments of the present disclosure provides a voice broadcast control device, comprising: A keyword extraction module, configured to extract keywords from the first notification message in response to receiving the first notification message; a message processing module, configured to process the first notification message based on the keyword to obtain a second notification message; The voice broadcast module is used to convert the second notification message into a voice message and voice broadcast the voice message.

[0006] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned voice broadcast control method when executing the computer program.

[0007] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned voice broadcast control method are implemented.

[0008] The beneficial effects of the voice broadcast control method, device, electronic device and storage medium provided by the embodiments of the present disclosure are: In the disclosed embodiment, the first device may be a smart terminal such as a smart phone, a tablet computer, or a laptop computer. Multiple APPs are installed in the first device, and the smart terminal can receive the first notification message through the multiple APPs. By extracting keywords from the first notification message, processing the first notification message based on the keywords, and removing irrelevant information, the obtained second notification message can better highlight the key content, allowing the user to grasp the key points more quickly. The second notification message is converted into a voice message for broadcast, which facilitates the user to obtain information when the screen cannot be viewed or both hands are occupied, thereby improving the convenience and flexibility of user use.

[0009] The disclosed embodiment extracts keywords from the first notification message, processes the first notification message based on the keywords, and performs voice broadcast, so that users can quickly understand the core content of the message without reading lengthy text, thereby greatly saving time and improving the efficiency of information acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, 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 disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A flowchart of a voice broadcast control method provided by an embodiment of the present disclosure; Figure 2 A structural block diagram of a voice broadcast control device provided in one embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A flow chart of a voice broadcast control method provided in an embodiment of the present disclosure, the method comprising: S101: In response to receiving a first notification message, extract keywords in the first notification message.

[0015] In this embodiment, the voice broadcast control method is applied to the processor of the first device. The first device can be a smart terminal such as a smart phone, a tablet computer, or a laptop computer. Multiple APPs are installed in the first device, and the smart terminal can receive the first notification message through the multiple APPs.

[0016] The first notification message may come from the server of the APP. Taking a news APP as an example, the news content provider uploads the latest news information to the server, and the server pushes the corresponding news first notification message to the first device on which the APP is installed according to the user's subscription and preference settings.

[0017] The first notification message may also come from other users' smart terminals. Taking social APP as an example, the dynamics, comments, private messages, etc. posted by users on Weibo are all the first notification messages received by other users.

[0018] The first notification message may also come from a third-party data interface. Taking a weather APP as an example, by accessing the data interface of the meteorological department, weather forecast information can be obtained and displayed to the user in the form of a first notification message.

[0019] The first notification message is usually a text message. If it is a voice message, voice recognition can be performed first to convert the voice message into a text message.

[0020] The keywords in the first notification message can be extracted using the existing TextRank algorithm. The TextRank algorithm considers words in the text as nodes and the co-occurrence relationship between words as edges to construct an undirected graph. The weight of each node is calculated iteratively until the weight converges, and the word with the higher weight is the keyword. You can also use a deep learning framework to build a language model for training, and extract keywords based on the trained language model. S102: Process the first notification message based on the keyword to obtain a second notification message.

[0021] In this embodiment, according to the extracted keywords, various processes can be performed on the first notification message. One of the processing methods can be to remove those information that has little association with the keywords and is insignificant. The obtained second notification message is more concise and clear, which can highlight the key content, enabling users to quickly focus on the most important information when receiving the notification without having to laboriously search for the key points among a large amount of redundant information.

[0022] Optionally, natural language processing tools can be used to perform part-of-speech tagging on the first notification message to identify the part of speech of each word, such as nouns, verbs, adjectives, adverbs, etc.; then perform dependency syntactic analysis to determine the grammatical relationships between the words in the sentence. For example, find the main components such as the subject, predicate, and object, as well as the relationship between the modifier and the modified; traverse each word in the first notification message to check whether it is directly related to the keyword or helps to convey the meaning of the keyword; remove the modifiers that have little relationship with the keyword to obtain the simplified second notification message.

[0023] For example, the first notification message received by a social app is: "Dear friends, last night in the Garden Square, we held a particularly wonderful and unforgettable party! Everyone had a super great time and the atmosphere was extremely warm." First, by extracting keywords from the above first notification message, the keywords of the first notification message are obtained as "party" and "happy".

[0024] Then, part-of-speech tagging is performed on the first notification message. For example, "dear" is an adjective, "friends" is a noun, "yesterday" is a time noun, "night" is a time noun, "in" is a preposition, "that" is a demonstrative pronoun, "super" is an adverb, "beautiful" is an adjective, "Garden Square" is a noun phrase, "we" is a pronoun, "held" is a verb, "a" is an article, "particularly" is an adverb, "wonderful" and "unforgettable" are adjectives, "party" is a noun, "everyone" is a pronoun, "all" is an adverb, "had" is a verb, "a super great" is an adverbial phrase, "time" is a noun, "atmosphere" is a noun, "extremely" is an adverb, and "warm" is an adjective.

[0025] Next, through dependency syntactic analysis, it is obtained that for the keyword "party", the verb "held" directly related to it is retained. For the keyword "happy", the expressions "had a super great" and "time" that reflect the happy state are retained. In addition, the time nouns "yesterday" and "night" also need to be retained.

[0026] Finally, the obtained second notification message is: "Last night, a party was held and everyone had a great time." Another way to process the first notification message is to process it differently according to different keywords to meet the personalized needs of users. For example, when encountering a second notification message containing a specific keyword, a special voice effect processing can be performed on it. The special voice effect can include adjusting the pitch, speed, timbre and other aspects of the voice, or adding a specific sound effect background.

[0027] For example, for keywords related to important work tasks, a more serious and clear voice effect can be used to highlight their importance; for celebrity keywords that users pay special attention to in entertainment news, a lively and infectious voice effect can be used. This processing method is conducive to increasing users' attention to specific messages, allowing users to more easily identify the content they care about among many notification messages, thereby improving the efficiency and satisfaction of users in obtaining information, and bringing users a more personalized and considerate user experience.

[0028] S103: Convert the second notification message into a voice message, and broadcast the voice message.

[0029] In this embodiment, the second notification message can be converted into a voice message through speech synthesis technology, and the voice message can be broadcast through the audio output device in the first device. Speech synthesis technology relies on a rich voice database and can accurately and efficiently convert text content into natural and fluent voice messages. By converting the second notification message into a voice message for broadcasting, it is greatly convenient for users, especially when users cannot view the screen, such as when the user is driving, doing outdoor sports, or their hands are busy with other matters and cannot directly view the notification message on the device screen. At the same time, for those users who need to perform multiple tasks at the same time, the method of this embodiment also provides great convenience. Users can obtain important information by listening to voice messages while handling other tasks without interrupting the current workflow, thereby greatly improving the efficiency and convenience of users in obtaining information.

[0030] It can be concluded from the above that this embodiment extracts keywords from the first notification message, processes the first notification message based on the keywords, removes irrelevant information, and obtains a second notification message that can better highlight key content, allowing users to grasp the key points more quickly. The second notification message is converted into a voice message for broadcast, which facilitates users to obtain information when they cannot view the screen or their hands are occupied, thereby improving the convenience and flexibility of user use.

[0031] This embodiment extracts keywords from the first notification message, processes the first notification message based on the keywords, and performs voice broadcast, so that users can quickly understand the core content of the message without reading lengthy text, thereby greatly saving time and improving the efficiency of information acquisition.

[0032] In one embodiment of the present disclosure, extracting keywords from the first notification message includes: Determining a first keyword set based on a message type of the first notification message; Performing word segmentation processing on the first notification message to obtain multiple first words in the first notification message; The matching degrees of the plurality of first words in the first notification message and the plurality of second words in the first keyword set are calculated respectively, and keywords are extracted from the plurality of first words based on the matching degree calculation results.

[0033] In this embodiment, the first keyword set is a set of predetermined keywords, considering that different message types usually have specific subject and field characteristics. For example, social messages may have keywords such as "friend request", "like", "comment", etc.; news push may have keywords such as "breakout", "hot spot", "exclusive", etc.; work notifications may have keywords such as "urgent", "meeting", "task", etc.; financial information may have keywords such as "stock", "exchange rate", "fund", etc. Therefore, by determining the first keyword set based on the message type, the search scope of keywords can be quickly narrowed down, and the efficiency of subsequent processing can be improved.

[0034] The first notification message can be split into multiple independent first words by using natural language processing technology, and on this basis, the matching degree between the multiple first words and the multiple second words in the first keyword set is calculated respectively. The matching degree can be calculated by various methods, such as string matching, using word vectors to calculate the similarity between the first word and the second word, etc. The similarity can be calculated by existing methods such as cosine similarity and Euclidean distance.

[0035] A threshold may be set to extract first words with a matching degree higher than the threshold as keywords. For example, if a first word has a high similarity to a second word in the first keyword set, it may be extracted as a keyword.

[0036] It can be concluded from the above that this embodiment determines the first keyword set according to the message type, can perform targeted keyword extraction for different fields and topics, can reduce unnecessary calculations and search scopes, and improve the speed of keyword extraction. Especially in the case of a large number of notification messages, the method of this embodiment can quickly filter out keywords and improve the efficiency of information processing.

[0037] In one embodiment of the present disclosure, the message type of the first notification message includes a first message classification and a second message classification; Determining a first keyword set based on a message type of the first notification message includes: determining a first message classification of the first notification message based on the process information of the first device; Determining a second keyword set based on the first message classification; Determining a second message classification of the first notification message based on the attribute information of the first notification message; The first keyword set is extracted from the second keyword set based on the second message classification.

[0038] In this embodiment, the process information of the first device refers to the relevant information of the program or task running on the first device. The process information of the first device can reflect the program or task running on the first device, and the first notification message can be preliminarily classified based on this to obtain the first message classification. For example, if the first device is running a news client, it can be determined that the first notification message belongs to a news message, and the first message is classified as a news message; if work management software is running, it can be determined that the first notification message is a work-related message type, and the first message is classified as a work-related message type.

[0039] The corresponding second keyword set may be determined according to the first message classification. For example, if the first message is classified as news, the second keyword set may include keywords related to various news topics, such as common keywords in the fields of politics, economy, technology, entertainment, etc.

[0040] The attribute information of the first notification message may include the source of the message, which may be a specific news media, a social platform, a work mailbox, etc. According to the source of the message, the first notification message may be classified in more detail. For example, if the source of the message is a financial news media, the second message may be classified as a financial news category.

[0041] Based on the second message classification, the most relevant keywords to the classification can be extracted from the second keyword set to form the first keyword set. For example, if the second message is classified as financial news, then keywords related to finance, such as stock codes, economic indicators, financial terms, etc., are extracted from the second keyword set as the first keyword set.

[0042] It can be concluded from the above that this embodiment determines the most suitable keyword set based on different device processes and message attributes, which can reduce unnecessary calculations and analyses and improve the efficiency of information processing.

[0043] In one embodiment of the present disclosure, respectively calculating the matching degree of multiple first words in the first notification message and multiple second words in the first keyword set, and extracting keywords from the multiple first words based on the matching degree calculation results, includes: Calculate first hash values ​​of multiple first words in the first notification message respectively; If the first hash value corresponding to any first word is the same as any second hash value in the hash table, determining any first word as a keyword in the first notification message; The hash table generation process includes: Calculate second hash values ​​of a plurality of second words in the first keyword set; A hash table is constructed based on the second hash values ​​and the corresponding second words; wherein the second hash values ​​in the hash table are different from each other.

[0044] In this embodiment, a specific hash function can be used to calculate the first hash value corresponding to each first word. The function of the hash function is to convert an input of any length into a numerical value (hash value) of fixed length, and different words usually get different hash values. Therefore, based on the uniqueness of the hash value, the matching degree of the first word and the second word can be calculated.

[0045] The first word and the second word can be hashed using common hash functions such as MD5 and SHA-1, or a custom hash function can be used. For example, assuming a simple hash function is used, the ASCII value of each character of the first word "party" is added, and then the modulus of a fixed number is taken to obtain the corresponding first hash value of 50.

[0046] The second hash value of the second word can be pre-calculated and saved in the hash table, and the initial value of the hash table is empty. The same hash function as the first hash value can be used to perform hash calculation on each second word to obtain the corresponding second hash value, and the second hash value is used as the index position of the hash table, and the second hash value and the corresponding second word are saved in the hash table. For example, the second hash value corresponding to the second word "party" is 50, and the second hash value corresponding to the second word "happy" is 80, then "party" is stored in position 50 of the hash table, and "happy" is stored in position 80 of the hash table.

[0047] In the hash table, each second hash value is different from each other, and each second hash value corresponds to a specific second word. If the second hash values ​​corresponding to two or more second words are the same, the two or more second words are saved in the corresponding positions in the hash table (that is, the positions determined by the second hash values).

[0048] On the basis of obtaining the hash table, for each first hash value of the first word, determine its corresponding position in the hash table, that is, the first position. You can traverse each first position in the hash table. If there is data at a first position in the hash table, it means that the first word corresponding to the first position has the same hash value as a second word in the first keyword set, and the first word corresponding to the first position is determined as the keyword of the first notification message. For example, if the first hash value of a first word "party" is 50, and there is data (that is, word) "party" at position 50 in the hash table, the first word "party" is determined as the keyword of the first notification message.

[0049] It can be concluded from the above that this embodiment utilizes the fast search characteristics of the hash table to determine the keywords in the first notification message in a relatively short time. Compared with the existing methods of calculating similarity through string matching or word vectors, both of which require comparing multiple first words and multiple second words one by one and have slow calculation speeds, the operations of calculating hash values ​​and traversing the hash table in the method of this embodiment are relatively simple and fast, which can greatly improve the efficiency of keyword extraction.

[0050] In one embodiment of the present disclosure, after the step of determining the first word having data at the corresponding first position in the hash table as a keyword of the first notification message, the voice broadcast control method further includes: Perform string matching on the keyword and the third word; the third word is the second word stored in the first position in the hash table; Filter keywords based on string matching results.

[0051] In this embodiment, it is considered that different words may obtain the same hash value, that is, the keyword found by the hash value may not be the real keyword, resulting in unnecessary keywords being extracted. In order to avoid the above problem, on the basis of preliminarily determining that a first word is a keyword by checking the hash table, the keyword can be further matched with the third word (that is, the second word stored in the first position of the hash table) by string matching. If the string matching result shows that the keyword is exactly the same as the third word or meets certain similarity conditions, the keyword can be retained; if the similarity conditions are not met, the keyword can be considered to be removed.

[0052] For example, the keyword initially determined by searching the hash table is "gathering", and the hash value of "gathering" obtained by hash calculation is 50. The second word (that is, the third word) stored at position 50 in the hash table is read, and the third word is string-matched with the keyword "gathering". If the string matching result shows that the two words are similar, it indicates that the keyword "gathering" is correctly extracted. For another example, the keyword initially determined by searching the hash table is "tourism", and the hash value of "tourism" obtained by hash calculation is 60. The second word (that is, the third word) stored at position 60 in the hash table is read, and the third word is string-matched with the keyword "tourism". If the string matching result shows that the two words are not similar, it indicates that the keyword "tourism" is incorrectly extracted and can be removed.

[0053] When performing string matching between the keyword and the third word, a variety of string matching algorithms such as exact matching or fuzzy matching may be used, and the strictness of the matching may be determined according to specific requirements.

[0054] It can be concluded from the above that this embodiment can screen and optimize keywords by matching the character string with the third word, thereby improving the quality of the keywords and ensuring that the keywords more accurately reflect the core content of the first notification message.

[0055] In one embodiment of the present disclosure, the first notification message is processed based on the keyword to obtain the second notification message, including: Generate summary information of the first notification message based on the keyword; The summary information and the first notification message are determined as the second notification message.

[0056] In this embodiment, based on the obtained keywords, a concise sentence can be constructed around the keywords to summarize the main content of the first notification message and generate summary information of the first notification message. The summary information and the first notification message are sent to the audio output device as the second notification message for voice broadcast. During the voice broadcast, the summary can be played first to allow the user to quickly understand the key content of the first notification message.

[0057] Specifically, important sentences or phrases may be selected from the first notification message as the summary based on factors such as the position of the sentence in the text (eg, the first sentence and the last sentence are usually more important), the number of keywords contained, and the length of the sentence.

[0058] For example, the first notification message is: "In today's era of rapid technological development, the application of smart devices is becoming more and more widespread. Technology company A recently launched a new smart watch, which not only has a stylish design, but also has powerful functions. It can monitor the user's health data in real time, such as heart rate, sleep quality, etc. At the same time, the watch also supports the recognition of multiple sports modes, providing convenience for users' sports and fitness. In addition, technology company A is constantly developing new technologies to improve the performance and user experience of smart devices. In the future, we have reason to believe that smart devices will play an important role in more fields." By extracting keywords from the text, we obtain keywords such as "technology company A", "smart watch", "fashion appearance", "health data (heart rate, sleep quality)", "exercise pattern recognition", "development of new technologies", and "improving performance and user experience".

[0059] In the text, "Technology company A recently launched a new smart watch, which not only has a stylish appearance design, but also has powerful functions. It can monitor the user's health data in real time, such as heart rate, sleep quality, etc. At the same time, the watch also supports the recognition of multiple sports modes, providing convenience for users' sports and fitness." This sentence contains multiple keywords such as "Technology Company A", "Smart Watch", "Fashionable Appearance", "Health Data", "Sports Mode Recognition", etc., and the length of the sentence is moderate, neither too short and insufficient information, nor too long and difficult to understand. Therefore, the above sentence can be selected as the summary: "Technology Company A launched a new smart watch with a stylish appearance, which can monitor health data (heart rate, sleep quality, etc.) in real time and support multiple sports mode recognition." It can be concluded from the above that this embodiment generates summary information of the first notification message based on keywords, which can help users quickly understand the core content of the notification message and improve the efficiency of information acquisition.

[0060] In an embodiment of the present disclosure, there are multiple first notification messages, and the first notification message is processed based on the keyword to obtain the second notification message. Determining the priority of each first notification message based on the keyword and the preference information input by the user; Determine the first notification message with the priority mark as the second notification message; Converting the second notification message into a voice message and announcing the voice message by voice includes: Determining the priority of the second notification message based on the priority tags corresponding to each second notification message; The second notification message is converted into a voice message based on the priority of the second notification message, and the voice message is voice broadcasted.

[0061] In this embodiment, the user can determine the type of notification message or information on a specific topic that he or she wishes to receive based on his or her own interests, needs, and concerns, and input the above information as preference information into the first device. By inputting preference information, the user can indicate preferences for different types of notification messages, such as news notifications, work task reminders, and social event invitations. For example, the user may be more concerned about work-related notification messages, but less interested in social event invitations. The user can also explicitly specify preferences for certain specific topics, such as technology, sports, entertainment, and finance, by inputting preference information. For example, the user may express a special interest in technology news and wish to receive notification messages about the latest technology product releases, technological innovation trends, and other aspects first.

[0062] Based on the keywords extracted from the first notification message and the preference information provided by the user about the content of interest, a level of importance can be set for each first notification message. For example, if the preference information input by the user indicates that the user is more interested in science and technology news, the first notification message containing the keywords "technology company", "new product", "smart device", etc. can be given a higher priority based on the keywords and preference information.

[0063] The first notification message with the priority mark is determined as the second notification message, so that the second notification message contains the priority information. When performing voice broadcast, the second notification message can be converted into a voice format and played in sequence according to the priority level. The high-priority notification message will be converted and broadcasted first, and the low-priority message will be processed later.

[0064] From the above, it can be concluded that this embodiment takes into account the user's preference information to determine the priority of the first notification message, can provide personalized services to users, enable users to obtain the most important information to them more quickly, avoid users being disturbed by a large number of irrelevant notification messages, and improve the efficiency of information acquisition.

[0065] Corresponding to the voice broadcast control method of the above embodiment, Figure 2 This is a structural block diagram of a voice broadcast control device provided by an embodiment of the present disclosure. For ease of description, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The voice broadcast control device 20 includes: a keyword extraction module 21, a message processing module 22 and a voice broadcast module 23. The keyword extraction module 21 is configured to extract keywords from the first notification message in response to receiving the first notification message; A message processing module 22, configured to process the first notification message based on the keyword to obtain a second notification message; The voice broadcast module 23 is used to convert the second notification message into a voice message and to broadcast the voice message.

[0066] In one embodiment of the present disclosure, the keyword extraction module 21 is specifically used for: Determining a first keyword set based on a message type of the first notification message; Performing word segmentation processing on the first notification message to obtain multiple first words in the first notification message; The matching degrees of the plurality of first words in the first notification message and the plurality of second words in the first keyword set are calculated respectively, and keywords are extracted from the plurality of first words based on the matching degree calculation results.

[0067] In one embodiment of the present disclosure, the keyword extraction module 21 is further used to: determining a first message classification of the first notification message based on the process information of the first device; Determining a second keyword set based on the first message classification; Determining a second message classification of the first notification message based on the attribute information of the first notification message; The first keyword set is extracted from the second keyword set based on the second message classification.

[0068] In one embodiment of the present disclosure, the keyword extraction module 21 is further used to: Calculate first hash values ​​of multiple first words in the first notification message; Traversing each first position in the hash table, determining the first word in the corresponding first position in the hash table with data as a keyword of the first notification message; the first position is the position corresponding to the first hash value; The hash table generation process includes: Calculate second hash values ​​of a plurality of second words in the first keyword set; A hash table is constructed based on the second hash values ​​and the corresponding second words; wherein the second hash values ​​in the hash table are different from each other.

[0069] In one embodiment of the present disclosure, the keyword extraction module 21 is further used to: Perform string matching on the keyword and the third word; the third word is the second word stored in the first position in the hash table; Filter keywords based on string matching results.

[0070] In one embodiment of the present disclosure, the message processing module 22 is specifically used to: Generate summary information of the first notification message based on the keyword; The summary information and the first notification message are determined as the second notification message.

[0071] In one embodiment of the present disclosure, the message processing module 22 is specifically used to: Determining the priority of each first notification message based on the keyword and the preference information input by the user; Determine the first notification message with the priority mark as the second notification message; Converting the second notification message into a voice message and announcing the voice message by voice includes: Determining the priority of the second notification message based on the priority tags corresponding to each second notification message; The second notification message is converted into a voice message based on the priority of the second notification message, and the voice message is voice broadcasted.

[0072] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0073] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0074] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0075] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0076] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the voice broadcast control method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0077] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0078] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0079] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0080] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0081] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0083] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0084] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A voice broadcast control method, applied to a first device, characterized in that: include: In response to receiving a first notification message, extracting keywords in the first notification message; Processing the first notification message based on the keyword to obtain a second notification message; The second notification message is converted into a voice message, and the voice message is voice broadcasted.

2. The voice broadcast control method according to claim 1, characterized in that: The extracting keywords from the first notification message includes: Determining a first keyword set based on a message type of the first notification message; Performing word segmentation processing on the first notification message to obtain multiple first words in the first notification message; The matching degrees of the plurality of first words in the first notification message and the plurality of second words in the first keyword set are respectively calculated, and the first words whose corresponding matching degrees meet the set conditions are determined as keywords of the first notification message.

3. The voice broadcast control method according to claim 2, characterized in that: The message type of the first notification message includes a first message classification and a second message classification; The determining the first keyword set based on the message type of the first notification message includes: determining a first message classification of the first notification message based on process information of the first device; Determining a second keyword set based on the first message classification; determining a second message classification of the first notification message based on the attribute information of the first notification message; The first keyword set is extracted from the second keyword set based on the second message classification.

4. The voice broadcast control method according to claim 2, characterized in that: The respectively calculating the matching degrees of the plurality of first words in the first notification message and the plurality of second words in the first keyword set, and determining the first words whose corresponding matching degrees satisfy the set conditions as the keywords of the first notification message, includes: Calculate first hash values ​​of multiple first words in the first notification message; Traversing each first position in the hash table, determining a first word having data in the corresponding first position in the hash table as a keyword of the first notification message; the first position is a position corresponding to the first hash value; The generation process of the hash table includes: Calculate second hash values ​​of a plurality of second words in the first keyword set; A hash table is constructed based on the second hash values ​​and the corresponding second words; wherein the second hash values ​​in the hash table are different from each other.

5. The voice broadcast control method according to claim 4, characterized in that: After the step of determining the first word having data at the corresponding first position in the hash table as a keyword of the first notification message, the voice broadcast control method further includes: Perform string matching on the keyword and a third word; the third word is the second word stored in the first position in the hash table; The keywords are screened based on the string matching results.

6. The voice broadcast control method according to claim 1, characterized in that: The processing of the first notification message based on the keyword to obtain the second notification message includes: generating summary information of the first notification message based on the keyword; The summary information and the first notification message are determined as the second notification message.

7. The voice broadcast control method according to claim 1, characterized in that: The first notification message is multiple, and the processing of the first notification message based on the keyword to obtain the second notification message includes: Determining the priority of each first notification message based on the keyword and the preference information input by the user; Determine the first notification message with the priority mark as the second notification message; The converting the second notification message into a voice message and voice broadcasting the voice message includes: Determining the priority of the second notification message based on the priority tags corresponding to the second notification messages; The second notification message is converted into a voice message based on the priority of the second notification message, and the voice message is voice broadcasted.

8. A voice broadcast control device, applied to a first device, characterized in that: include: A keyword extraction module, configured to extract keywords from the first notification message in response to receiving the first notification message; a message processing module, configured to process the first notification message based on the keyword to obtain a second notification message; The voice broadcast module is used to convert the second notification message into a voice message and voice broadcast the voice message.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, 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 7 are implemented.

Images