CN111555960A - Method for generating information - Google Patents
Method for generating information Download PDFInfo
- Publication number
- CN111555960A CN111555960A CN202010331180.7A CN202010331180A CN111555960A CN 111555960 A CN111555960 A CN 111555960A CN 202010331180 A CN202010331180 A CN 202010331180A CN 111555960 A CN111555960 A CN 111555960A
- Authority
- CN
- China
- Prior art keywords
- unread
- information
- message
- keyword
- unread messages
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 230000001939 inductive effect Effects 0.000 claims abstract description 38
- 230000006698 induction Effects 0.000 claims abstract description 37
- 230000004044 response Effects 0.000 claims abstract description 13
- 230000011218 segmentation Effects 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
- H04L51/18—Commands or executable codes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/02—Details
- H04L12/16—Arrangements for providing special services to substations
- H04L12/18—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast
- H04L12/1813—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast for computer conferences, e.g. chat rooms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services
Abstract
The embodiment of the disclosure discloses a method for generating information. One embodiment of the method comprises: in response to determining that the number of unread messages of the target object is equal to or greater than a preset threshold, obtaining unread messages of the target object; extracting at least one key phrase from the obtained unread message, wherein the key phrase comprises at least one key word aiming at the same event; aiming at a key phrase in at least one key phrase, generating induction information corresponding to the key phrase according to semantic information corresponding to the key word in the key phrase; and displaying the inductive information. The embodiment enables the user to quickly know the contents of a large number of unread messages by reading the inductive information, and improves the efficiency of reading the unread messages.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to an information generation method.
Background
With the popularization of intelligent terminal equipment such as mobile phones, the existing intelligent terminal equipment can be used as a traditional communication tool, can realize functions of making a call, sending a short message and the like, and becomes an essential modern communication tool in daily life. According to the requirements of the user, the user can install various applications in the intelligent terminal device, for example, applications which very achieve a social function, such as social software (e.g., QQ, wechat, etc.), can be installed.
When the smart phone is used as a modern communication tool, a large amount of unread messages often appear. In addition, a lot of messages which are not important or repeated often exist in a large number of unread messages, and a user wastes a large amount of time when looking up the unread messages. For example, when the chat software is opened to view the (99+) voice information, it takes a lot of time if each item is consulted. Therefore, there is a need for a method that can quickly refer to unread messages.
Disclosure of Invention
The embodiment of the disclosure provides a method and a device for generating information.
In a first aspect, an embodiment of the present disclosure provides an information generating method, where the method includes: in response to determining that the number of unread messages of the target object is equal to or greater than a preset threshold, obtaining unread messages of the target object; extracting at least one key phrase from the obtained unread message, wherein the key phrase comprises at least one key word aiming at the same event; aiming at a key phrase in at least one key phrase, generating induction information corresponding to the key phrase according to semantic information corresponding to the key word in the key phrase; and displaying the inductive information.
In a second aspect, an embodiment of the present disclosure provides an apparatus for information generation, the apparatus including: an acquisition unit configured to acquire an unread message of a target object in response to determining that the number of unread messages of the target object is equal to or greater than a preset threshold; an extracting unit configured to extract at least one keyword group from the obtained unread message, wherein the keyword group comprises at least one keyword for the same event; the generating unit is configured to generate induction information corresponding to a key phrase according to semantic information corresponding to the key word in the key phrase aiming at the key phrase in at least one key phrase; a first display unit configured to display the induction information.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including: one or more processors; a storage device having one or more programs stored thereon which, when executed by one or more processors, cause the one or more processors to implement the method described above.
In a fourth aspect, embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, where the program is to implement the above-mentioned method when executed by a processor.
According to the method and the device for generating information, under the condition that the number of the unread messages of the target object is determined to be equal to or larger than the preset threshold, the unread messages of the target object can be obtained, then at least one keyword group is extracted from the obtained unread messages, and then, aiming at the keyword group in the at least one keyword group, inductive information corresponding to the keyword group can be generated according to semantic information corresponding to the keyword in the keyword group, and finally, the inductive information is displayed, so that a user can quickly know the content of a large number of unread messages by reading the inductive information, and the efficiency of reading the unread messages by the user is improved.
Drawings
Other features, objects and advantages of the disclosure will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which some embodiments of the present disclosure may be applied;
FIG. 2 is a flow diagram for one embodiment of a method of information generation according to the present disclosure;
FIG. 3 is a schematic diagram of one application scenario of a method of information generation in accordance with an embodiment of the present disclosure;
FIG. 4 is a flow diagram of yet another embodiment of a method of information generation according to the present disclosure;
FIG. 5 is a schematic block diagram illustration of one embodiment of an apparatus for information generation in accordance with the present disclosure;
FIG. 6 is a schematic structural diagram of an electronic device suitable for use in implementing embodiments of the present disclosure.
Detailed Description
The present disclosure is described in further detail below with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that, in the present disclosure, the embodiments and features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 illustrates an exemplary system architecture 100 to which the method of information generation or the apparatus of information generation of embodiments of the present disclosure may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have installed thereon various communication client applications, such as social platform software, instant messaging tools, web browser applications, shopping applications, search applications, mailbox clients, and the like.
The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices having a display screen and supporting message browsing, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers, desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.
The server 105 may be a backend server that provides various services. The background server can perform processing such as keyword extraction on the acquired data such as the unread message, and feed back and display the processing result (such as inductive information) to the terminal device.
It should be noted that the method for generating information provided by the embodiment of the present disclosure may be executed by the terminal devices 101, 102, and 103, or may be executed by the server 105. Accordingly, the information generating device may be provided in the terminal apparatuses 101, 102, and 103, or may be provided in the server 105. And is not particularly limited herein.
The server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster formed by multiple servers, or may be implemented as a single server. When the server is software, it may be implemented as multiple pieces of software or software modules, for example, to provide distributed services, or as a single piece of software or software module. And is not particularly limited herein.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Note that the terminal devices 101, 102, and 103 may also perform processing such as keyword group extraction on the unread message, in this case, the method of generating the information may also be executed by the terminal devices 101, 102, and 103, and accordingly, the apparatus for generating the information may also be provided in the terminal devices 101, 102, and 103. At this point, the exemplary system architecture 100 may not have the server 105 and the network 104.
With continued reference to fig. 2, a flow 200 of one embodiment of a method of information generation in accordance with the present disclosure is shown. The information generation method comprises the following steps:
In the present embodiment, the execution subject of the method for information generation may be, for example, the terminal device or the server shown in fig. 1. Specifically, if the execution main body of the information generation method is a server, the execution main body may acquire an unread message from a terminal device, which a user uses to send, receive, and browse messages by using the unread message in a wired connection manner or a wireless connection manner; if the execution main body of the information generation method is the terminal equipment where the user is located, the execution main body can locally acquire the unread message. Here, a specific implementation of the information generation method will be described by taking a terminal device where a user is located as an execution subject.
In this embodiment, the execution body may determine whether the number of unread messages of the target object is greater than or equal to a preset threshold. The target object may be an object that can be communicated with the designated software (e.g., social software) by text, voice, and the like. For example, the object may be a chat object in the social software that contains only one friend, or the object may also be a chat group in the social software that contains multiple friends. If the number of unread messages of the target object is greater than or equal to the preset threshold, the execution body may obtain the unread messages of the target object. If the number of unread messages of the target object is less than the preset threshold, the execution body may not perform any processing. Here, the preset threshold value can be set by those skilled in the art according to actual needs. It is understood that different users may set the preset threshold according to their own needs, and there is no unique limitation here. As an example, the user may determine the preset threshold value as 30, and if it is determined that the number of unread messages of a certain chat group is greater than or equal to 30, the execution subject may obtain all the unread messages of the chat group.
In general, the execution body may determine the number of unread messages for each object by monitoring each object. Optionally, the execution main body may monitor each object in real time, and once the number of unread messages is greater than or equal to a preset threshold, the execution main body may obtain the unread messages of the object to perform induction processing on the obtained unread messages. Or, the execution main body may also monitor each object at regular time, so as to determine the number of unread messages of each object at regular time, and if the number of unread messages is greater than or equal to a preset threshold, the execution main body may obtain the unread messages of the object, so as to perform induction processing on the obtained unread messages. Of course, the execution subject can also summarize the unread messages through the operation behaviors of the user without monitoring each object. As an example, after the user performs an operation such as clicking a preset control (e.g., "information summarization" control), the execution body may directly perform summarization on the unread message. Or, after the user lights the screen of the terminal device or opens the program where the target object is located, the execution main body directly performs induction processing on the unread message.
In this embodiment, for the unread messages obtained in step 201, each unread message may belong to the same event, or each unread message may be a message belonging to at least two events. Therefore, after acquiring the unread message, the execution subject (e.g., the server shown in fig. 1) may extract at least one keyword group from the unread message according to events in various ways. For any keyword group, the keyword group may include at least one keyword belonging to the same event. As an example, each unread message may be semantically analyzed, and each unread message may be divided into different event groups according to the semantic analysis result, and keywords extracted from the unread messages of the same event group may be divided into the same keyword group.
In some optional implementation manners of this embodiment, before extracting at least one keyword group from the obtained unread message, the execution main body may further determine whether a voice-type unread message exists in the obtained unread message. If the obtained unread message includes a voice-type unread message, the execution subject may convert the obtained voice-type unread message into a text-type unread message, so that the execution subject may extract at least one keyword group from the text-type unread message. It is to be understood that the unread message may also include a picture type unread message, and the execution subject may perform image recognition on the picture and the like, so that the picture and the like may be converted into a text type unread message. The implementation mode can convert the non-text unread messages in the unread messages so as to extract the keywords of the text messages in the follow-up process, thereby enriching the extracted keywords.
In this embodiment, based on the at least one keyword group extracted in step 202, for any one of the keyword groups, the execution main body may process each keyword in the keyword group in various ways, so as to obtain semantic information of each keyword in the keyword group and generate induction information corresponding to the keyword group. As an example, the execution main body analyzes the part of speech, the semantic relationship between the keywords, and the like of each keyword in the keyword group, so that each keyword in the keyword group can be sorted, and finally, the sorted keywords are integrated, so that the corresponding inductive information can be obtained. As an example, the key phrases extracted by the execution subject include: today, afternoon, Nanjing road, weather, shopping, emphasis and depression, the induction information correspondingly generated can be that the weather is bad, the shopping cannot be realized and the depression is caused according to the semantic information corresponding to the key words in the key word group.
In some optional implementation manners of this embodiment, the execution main body may further implement, by other manners, that induction information corresponding to the keyword group is generated according to semantic information corresponding to the keyword in the keyword group. Specifically, for a keyword group of at least one keyword group, the execution subject may input the keyword group into a pre-trained message generation model, so as to obtain induction information corresponding to the keyword group. The message generation model is used for generating corresponding induction information according to the semantic information of each keyword in the keyword group. The message generation model may be a model trained in various ways, and is not limited uniquely here. The scheme provided by the implementation mode can directly obtain induction information corresponding to the key phrase through the message generation model, and further improves the efficiency of information induction.
In some optional implementation manners of this embodiment, the message generation model may specifically generate corresponding inductive information through the following steps: the method comprises the steps of adopting a pre-trained message generation model, mapping keywords in a keyword group into keyword vectors according to a dictionary preset in the message generation model, generating hidden layer states of model coding moments according to the keyword vectors and messages to generate semantic vectors, generating hidden layer states of model decoding moments according to the semantic vectors and the messages, and obtaining induction information through calculation. The message generation model is a model based on a recurrent neural network. Specifically, the message generation model may be a seq2seq model, and includes a coding end and a decoding end, in the message generation model, the keywords in the keyword group may be sequentially input to the coding end of the message generation layer model, and after the keywords are mapped to the keyword vectors by using a preset dictionary, the keyword group may be converted into a fixed-length semantic vector group. The semantic vector group includes information of the keyword vector group inputted to the encoding side. And finally, inputting the semantic vector of the keyword into a decoding end, so that induction information can be obtained through calculation. The scheme provided by the implementation mode enables the computer to process the language to be deep into the semantic understanding level, enables the text semantics of the generated inductive information to be smooth, and improves the quality of the generated inductive information.
In this embodiment, the execution subject may generate inductive information corresponding to each keyword group based on step 203. The execution body may then display the generated summary information to the user. The user can know the related events of all unread messages by looking at the displayed inductive information, and then the user can independently look at the unread messages in detail or skip the unread messages.
In some optional implementations of this embodiment, after the execution body displays the summary information to the user, each unread message may be marked as read directly. Alternatively, each unread message may also be marked as unread after the execution body displays the summary information to the user. Under the condition that the mark is unread, if the user needs to view the unread message in detail, the user can click to view the unread message, the click-to-view operation can be regarded as read marking operation, and the execution main body can mark the unread message clicked and viewed by the user as read message. If the user does not need to view the unread messages in detail, the user can execute the read marking operation on the unread messages by clicking a preset control and the like, and the execution main body can mark the obtained unread messages as read messages. The scheme disclosed by the implementation mode can mark each unread message as read through the read marking operation of the user, thereby avoiding the risk that the summarized unread message is obtained and summarized again and improving the information summarizing efficiency.
In some optional implementation manners of this embodiment, after the execution main body generates the inductive information corresponding to each keyword group, the execution main body may directly display the generated inductive information to the user. Alternatively, the execution main body may detect whether the user has performed a preset operation after generating the induction information corresponding to each keyword group. The execution body may display the inductive information if a user performs a preset operation. If the user does not perform the preset operation, the execution main body does not need to display the induction information. The preset operation may be operations of clicking a preset control, sending designated information, and the like, where the preset operation may be set according to actual requirements. The scheme provided by the implementation mode can enable the user to independently select whether to check the inductive information or not, and the user experience is improved.
With continued reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of the method of information generation according to the present embodiment. In the application scenario of fig. 3, in a case that the terminal device determines that the number of unread messages of a target object (such as the chat group in fig. 3) is equal to or greater than a preset threshold, the unread messages of the target object may be obtained; then, the terminal device can extract the key phrases corresponding to the events from the obtained unread messages; then, for any key phrase in each key phrase, the terminal device may generate inductive information corresponding to the key phrase according to semantic information corresponding to the key word in the key phrase, as shown in fig. 3, the obtained unread message relates to two events, and thus may generate two pieces of inductive information, "content 1" and "content 2"; finally, the terminal device may display the generated summary information "content 1" and "content 2".
In the method for generating information provided by the above embodiment of the present disclosure, under the condition that it is determined that the number of unread messages of the target object is equal to or greater than the preset threshold, the unread messages of the target object may be obtained, then at least one keyword group is extracted from the obtained unread messages, then, for a keyword group in the at least one keyword group, induction information corresponding to the keyword group may be generated according to semantic information corresponding to the keyword in the keyword group, and finally, the induction information is displayed, so that a user may quickly know the content of a large number of unread messages by reading the induction information, and the efficiency of reading the unread messages by the user is improved.
With further reference to fig. 4, a flow 400 of yet another embodiment of a method of information generation is shown. The process 400 of the information generating method includes the following steps:
In this embodiment, based on the unread message obtained in step 401, the execution main body may perform word segmentation processing on the text of the unread message in various ways, so as to obtain a word segmentation set of each unread message.
As an example, the full segmentation method may be used to segment words of each unread message, and all possible words matching the language lexicon are segmented from the unread message first, and then the optimal segmentation result is determined by using the statistical language model. Taking the unread message as 'Changjiang river bridge in Nanjing city' as an example, the language lexicon matching can be firstly carried out, and all matched words, namely Nanjing, City, Changjiang river, bridge, Nanjing city, Changjiang river bridge, city leader, Jiangtang bridge and bridge, can be found; the words are represented in the form of word lattices (word lattices), then path search is performed based on the word lattices, and an optimal path is found based on a statistical language model (such as an N-Gram model). And if the result shows that the language model of the Yangtze river bridge in Nanjing is the highest score, the Yangtze river bridge in Nanjing is the optimal segmentation of the Yangtze river bridge in Nanjing. Here, the N-Gram Model is a common Language Model, and for Chinese, it may be referred to as Chinese Language Model (CLM). The N-Gram model is based on the assumption that the occurrence of the nth word is only related to the first N-1 words and not to any other words, and the probability of the whole sentence is the product of the occurrence probabilities of the words, which can be obtained by directly counting the number of times that the N words occur simultaneously from the corpus. Of course, the unread message may also obtain corresponding participles through other word segmentation methods, which are not listed here.
In this embodiment, based on the word segmentation set of each unread message obtained in step 402, the execution main body may process the word segmentation in the word segmentation set of each unread message in various ways, so that the unread messages may be grouped according to events. As an example, for a set of participles of any unread message, an event to which the unread message belongs may be determined according to the part of speech of each participle in the set of participles. For example, it is possible to understand what the sender of the unread message mainly speaks according to "noun, person name, place name", etc., understand the tense of the sender description of the unread message according to "morpheme, time word", etc., understand what the sender description of the unread message does according to "morpheme, verb, side verb, name verb", etc., understand the attitude of the sender of the unread message according to "number word, quantifier, sigh word, word", etc., and comprehensively consider the respective parts of speech, i.e., determine the specific event to which the unread message belongs.
In this embodiment, after the execution body groups the unread messages according to the events, the unread messages in the same group belong to the same event. Therefore, the execution subject may adopt various means to extract the keyword from the participles belonging to the participle set of the unread messages in the same group, so as to obtain the keyword group of the event.
As an example, the executing entity may use a word frequency-inverse file frequency method to perform importance calculation on the participles in the participle set of the unread messages belonging to the same group, and then select the participles as keywords or score the importance of the participles based on the importance. The main idea of the Term Frequency-inverse document Frequency method is that if a word or phrase appears frequently (TF) in one article and rarely appears in other articles, the word or phrase is considered to have good category discrimination capability and is suitable for classification. The Inverse Document Frequency (IDF) mainly means that if fewer documents contain a certain word or phrase, the larger the IDF is, the word or phrase has a good category distinguishing capability. Thus, using the word frequency-inverse document frequency method, the importance of a word or phrase within an article can be calculated.
In some optional implementations of this embodiment, the execution subject may obtain the keyword group by: and performing word segmentation processing on each word segmentation based on the part-of-speech of the word segmentation of each unread message aiming at the unread message in the same group to obtain a corresponding key word group, wherein the word segmentation processing comprises classification, de-duplication and combination. The scheme provided by the implementation mode can classify each participle according to the part of speech, so that verb classification, noun classification, time-like language classification and the like can be obtained. It will be appreciated that since each category may be made up of multiple unread messages, the same or similar tokens may be included in the category, at which time the same or similar tokens may be deduplicated. Finally, the de-duplicated results may be segmented and combined to obtain a keyword, for example, the three segments "the bridge of Yangtze river of Nanjing City" may be combined to obtain a keyword "the bridge of Yangtze river of Nanjing City".
In this embodiment, the contents of step 401, step 405, and step 406 are the same as or similar to the contents of step 210, step 203, and step 204 in the above embodiments, respectively, and are not repeated here.
In some optional implementation manners of this embodiment, after the summary information is displayed, if it is determined that the user performs a viewing operation on an unread message corresponding to any summary information, the execution main body may open a display interface of the unread message. At this time, the user can view the unread messages in the event packet corresponding to the summary information. The scheme provided by the implementation mode can enable the user to read the unread message aiming at the event, avoid the user from wasting time to search the unread message of the corresponding event, and further improve the efficiency of reading the unread message by the user.
In some optional implementation manners of this embodiment, after grouping the unread messages according to the event, the execution body may set different identifiers for the unread messages in different groups, respectively. The identification here may be a font, a font size, a color of a character, a background of a character, etc. For example, after the unread message is divided into two event groups, the font of the unread message in one of the groups may be set as a song font, and the font of the unread message in the other group may be set as a regular font.
In some optional implementations of the present embodiment, the method for generating information disclosed in the present application may be applied to social applications. The target object may be a social object in a social application. The method for generating information disclosed in the present application may also be applied to, for example, a user-customer service communication of an e-commerce application, etc., and is not limited to the above.
In some optional implementations of the embodiment, the target object may be a social object including at least two social users in a social application. For example, the target object may be a group of chat users in the chat software. After the execution subject generates the induction information corresponding to the keyword group, the execution subject may further execute the following steps: for any inductive information, determining an unread message for generating the inductive information; determining a social user who sent the determined unread message from among the at least two social users; the determined social user is displayed while the inductive information is displayed. According to the scheme provided by the implementation mode, the summary information is displayed, and the users participating in the event communication are displayed at the same time, so that the users can read the summary information and know the participants of the corresponding events, the summary information is enriched, and the user experience is further improved.
As can be seen from fig. 4, compared with the embodiment corresponding to fig. 2, the flow 400 of the information generating method in this embodiment embodies a step of extracting at least one keyword group from the unread message. Therefore, the scheme described in the embodiment can perform event grouping on the unread messages according to the word segmentation of the unread messages, so that the grouping of the unread messages is more accurate, and the accuracy of the obtained inductive information is improved.
With further reference to fig. 5, as an implementation of the methods shown in the above-mentioned figures, the present disclosure provides an embodiment of an apparatus for information generation, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable to various electronic devices.
As shown in fig. 5, the information generation apparatus 500 of the present embodiment includes: an acquisition unit 501, an extraction unit 502, a generation unit 503, and a first display unit 504. Wherein the obtaining unit 501 is configured to obtain the unread message of the target object in response to determining that the number of unread messages of the target object is equal to or greater than a preset threshold; the extracting unit 502 is configured to extract at least one keyword group from the obtained unread message, wherein the keyword group includes at least one keyword for the same event; the generating unit 503 is configured to generate induction information corresponding to a keyword group according to semantic information corresponding to the keyword in the keyword group for the keyword group in at least one keyword group; the first display unit 504 is configured to display summary information.
In some optional implementations of this embodiment, the apparatus 500 further includes: a conversion unit configured to convert the voice type unread message into a text type unread message in response to determining that the voice type unread message exists in the acquired unread message.
In some optional implementations of this embodiment, the extracting unit 502 includes: the word segmentation module is configured to perform word segmentation on the acquired text of the unread message to obtain a word segmentation set of each unread message; the grouping module is configured to group the unread messages according to events based on the participles in the participle set of the unread messages; and the extraction module is configured to extract keywords from the participles in the participle set of the unread messages in the same group to obtain corresponding keyword groups.
In some optional implementations of this embodiment, the extraction module is further configured to: and performing word segmentation processing on each word segmentation based on the part-of-speech of the word segmentation of each unread message aiming at the unread message in the same group to obtain a corresponding key word group, wherein the word segmentation processing comprises classification, de-duplication and combination.
In some optional implementations of this embodiment, the apparatus 500 further includes: and the opening unit is configured to respond to the viewing operation of the user on the unread messages corresponding to any inductive information, and open the display pages of the unread messages so that the user can view the unread messages in the groups corresponding to the inductive information.
In some optional implementations of this embodiment, the apparatus 500 further includes: and the setting unit is configured to set different identifications for the unread messages in different groups respectively.
In some optional implementations of this embodiment, the apparatus 500 further includes: and the marking unit is configured to mark the acquired unread message as a read message in response to a read marking operation of the user.
In some optional implementations of the present embodiment, the first display unit 504 is further configured to: and responding to the preset operation of the user, and displaying the inductive information.
In some optional implementations of this embodiment, the generating unit 503 is further configured to: and aiming at a key phrase in at least one key phrase, inputting the key phrase into a pre-trained message generation model to obtain induction information corresponding to the key phrase, wherein the message generation model is used for generating corresponding induction information according to semantic information of each key word in the key phrase.
In some optional implementations of this embodiment, the generating unit 503 is further configured to: mapping keywords in the keyword group into keyword vectors by adopting a pre-trained message generation model according to a dictionary preset in the message generation model, wherein the message generation model is a model based on a recurrent neural network; generating a semantic vector according to the keyword vector and the hidden layer state of the message generation model at the coding moment; and calculating to obtain induction information according to the semantic vector and the hidden layer state of the message generation model at the decoding moment.
In some optional implementations of the embodiment, the apparatus 500 is applied to a social class application, and the target object is a social object in the social class application.
In some optional implementations of this embodiment, the social object includes at least two social users; the apparatus 500 further comprises: a first determination unit configured to determine, for any of the inductive information, an unread message for generating the inductive information; a second determining unit configured to determine, from among the at least two social users, a social user who sent the determined unread message; a second display unit configured to display the determined social user while displaying the induction information.
The units recited in the apparatus 500 correspond to the various steps in the method described with reference to fig. 2. Thus, the operations and features described above for the method are equally applicable to the apparatus 500 and the units included therein, and are not described in detail here.
Referring now to fig. 6, shown is a schematic diagram of an electronic device (e.g., terminal device in fig. 1) 600 suitable for use in implementing embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 6, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of embodiments of the present disclosure. It should be noted that the computer readable medium described in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In embodiments of the present disclosure, however, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: in response to determining that the number of unread messages of the target object is equal to or greater than a preset threshold, obtaining unread messages of the target object; extracting at least one key phrase from the obtained unread message, wherein the key phrase comprises at least one key word aiming at the same event; aiming at a key phrase in at least one key phrase, generating induction information corresponding to the key phrase according to semantic information corresponding to the key word in the key phrase; and displaying the inductive information.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, an extraction unit, a generation unit, and a first display unit. Where the names of the units do not constitute a limitation on the units themselves in some cases, for example, the acquiring unit may also be described as "a unit that acquires an unread message of a target object in response to determining that the number of unread messages of the target object is equal to or greater than a preset threshold".
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.
Claims (14)
1. A method of information generation, the method comprising:
in response to determining that the number of unread messages of a target object is equal to or greater than a preset threshold, obtaining the unread messages of the target object;
extracting at least one keyword group from the obtained unread message, wherein the keyword group comprises at least one keyword aiming at the same event;
aiming at a key phrase in the at least one key phrase, generating induction information corresponding to the key phrase according to semantic information corresponding to the key word in the key phrase;
and displaying the inductive information.
2. The method of claim 1, further comprising:
in response to determining that a voice-type unread message exists in the obtained unread messages, converting the voice-type unread messages to text-type unread messages.
3. The method according to claim 1 or 2, wherein the extracting at least one keyword group from the obtained unread message comprises:
performing word segmentation processing on the acquired text of the unread message to obtain a word segmentation set of each unread message;
grouping the unread messages according to events based on the participles in the participle set of the unread messages;
and extracting keywords from the participles in the participle set of the unread messages in the same group to obtain corresponding keyword groups.
4. The method according to claim 3, wherein the extracting keywords from the participles in the participle set of the unread messages in the same group to obtain a corresponding keyword group comprises:
and aiming at the unread messages in the same group, performing word segmentation processing on each word segmentation based on the part-of-speech of the word segmentation of each unread message to obtain a corresponding key word group, wherein the word segmentation processing comprises classification, duplication removal and combination.
5. The method of claim 3, wherein after displaying the summary information, the method further comprises:
and responding to the viewing operation of the user for the unread messages corresponding to any inductive information, and opening the display page of the unread messages so as to enable the user to view the unread messages in the groups corresponding to the inductive information.
6. The method of claim 5, further comprising:
and respectively setting different identifications for the unread messages in different groups.
7. The method according to any one of claims 1 to 6, further comprising:
and marking the acquired unread message as a read message in response to the read marking operation of the user.
8. The method of any of claims 1-7, wherein the displaying the summary information comprises:
and responding to preset operation of a user, and displaying the inductive information.
9. The method according to any one of claims 1 to 8, wherein the generating, for a keyword group of the at least one keyword group, induction information corresponding to the keyword group according to semantic information corresponding to a keyword in the keyword group includes:
and aiming at the key phrase in the at least one key phrase, inputting the key phrase into a pre-trained message generation model to obtain induction information corresponding to the key phrase, wherein the message generation model is used for generating corresponding induction information according to semantic information of each key word in the key phrase.
10. The method according to claim 9, wherein the inputting a pre-trained message generation model into the keyword group of the at least one keyword group to obtain induction information corresponding to the keyword group comprises:
mapping keywords in the keyword group into keyword vectors by adopting a pre-trained message generation model according to a dictionary preset in the message generation model, wherein the message generation model is a model based on a recurrent neural network;
generating a semantic vector according to the keyword vector and the hidden layer state of the message generation model at the coding moment;
and calculating to obtain induction information according to the semantic vector and the hidden layer state of the message generation model at the decoding moment.
11. The method according to one of claims 1 to 10, wherein the method is applied to a social application program, and the target object is a social object in the social application program.
12. The method of claim 11, wherein the social objects comprise at least two social users;
after generating the induction information corresponding to the keyword group, the method further comprises:
for any inductive information, determining an unread message for generating the inductive information;
determining, from the at least two social users, a social user that sent the determined unread message;
the determined social user is displayed while the inductive information is displayed.
13. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-12.
14. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010331180.7A CN111555960A (en) | 2020-04-24 | 2020-04-24 | Method for generating information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010331180.7A CN111555960A (en) | 2020-04-24 | 2020-04-24 | Method for generating information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111555960A true CN111555960A (en) | 2020-08-18 |
Family
ID=72003943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010331180.7A Pending CN111555960A (en) | 2020-04-24 | 2020-04-24 | Method for generating information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111555960A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283238A (en) * | 2021-05-19 | 2021-08-20 | 上海明略人工智能(集团)有限公司 | Text data processing method and device, electronic equipment and storage medium |
| WO2022135411A1 (en) * | 2020-12-25 | 2022-06-30 | 维沃移动通信有限公司 | Video call method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682092A (en) * | 2012-04-25 | 2012-09-19 | 北京神州泰岳软件股份有限公司 | Method for searching message in instant messenger (IM) system and IM client side |
| CN103369121A (en) * | 2012-04-09 | 2013-10-23 | 腾讯科技（深圳）有限公司 | Unread message display method and device |
| US20170142036A1 (en) * | 2015-11-17 | 2017-05-18 | International Business Machines Corporation | Summarizing and visualizing information relating to a topic of discussion in a group instant messaging session |
| CN108600083A (en) * | 2018-03-30 | 2018-09-28 | 上海掌门科技有限公司 | Message prompt method and equipment |
| CN109325233A (en) * | 2018-09-27 | 2019-02-12 | 北京安云世纪科技有限公司 | Global semantic understanding method, apparatus, computer equipment and storage medium |
| CN110738056A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN110750619A (en) * | 2019-08-15 | 2020-02-04 | 中国平安财产保险股份有限公司 | Chat record keyword extraction method and device, computer equipment and storage medium |
| CN110881056A (en) * | 2018-09-05 | 2020-03-13 | 百度在线网络技术（北京）有限公司 | Method and device for pushing information |
-
2020
- 2020-04-24 CN CN202010331180.7A patent/CN111555960A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103369121A (en) * | 2012-04-09 | 2013-10-23 | 腾讯科技（深圳）有限公司 | Unread message display method and device |
| CN102682092A (en) * | 2012-04-25 | 2012-09-19 | 北京神州泰岳软件股份有限公司 | Method for searching message in instant messenger (IM) system and IM client side |
| US20170142036A1 (en) * | 2015-11-17 | 2017-05-18 | International Business Machines Corporation | Summarizing and visualizing information relating to a topic of discussion in a group instant messaging session |
| CN108600083A (en) * | 2018-03-30 | 2018-09-28 | 上海掌门科技有限公司 | Message prompt method and equipment |
| CN110738056A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN110881056A (en) * | 2018-09-05 | 2020-03-13 | 百度在线网络技术（北京）有限公司 | Method and device for pushing information |
| CN109325233A (en) * | 2018-09-27 | 2019-02-12 | 北京安云世纪科技有限公司 | Global semantic understanding method, apparatus, computer equipment and storage medium |
| CN110750619A (en) * | 2019-08-15 | 2020-02-04 | 中国平安财产保险股份有限公司 | Chat record keyword extraction method and device, computer equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022135411A1 (en) * | 2020-12-25 | 2022-06-30 | 维沃移动通信有限公司 | Video call method and device |
| CN113283238A (en) * | 2021-05-19 | 2021-08-20 | 上海明略人工智能(集团)有限公司 | Text data processing method and device, electronic equipment and storage medium |
| CN113283238B (en) * | 2021-05-19 | 2023-12-22 | 上海明略人工智能(集团)有限公司 | Text data processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107066449B (en) | Information pushing method and device | |
| US9886501B2 (en) | Contextual content graph for automatic, unsupervised summarization of content | |
| US9881082B2 (en) | System and method for automatic, unsupervised contextualized content summarization of single and multiple documents | |
| US10558701B2 (en) | Method and system to recommend images in a social application | |
| WO2015185019A1 (en) | Semantic comprehension-based expression input method and apparatus | |
| US10423649B2 (en) | Natural question generation from query data using natural language processing system | |
| CN112507715A (en) | Method, device, equipment and storage medium for determining incidence relation between entities | |
| CN111753551B (en) | Information generation method and device based on word vector generation model | |
| WO2020182123A1 (en) | Method and device for pushing statement | |
| WO2022166613A1 (en) | Method and apparatus for recognizing role in text, and readable medium and electronic device | |
| WO2021063089A1 (en) | Rule matching method, rule matching apparatus, storage medium and electronic device | |
| CN111930792B (en) | Labeling method and device for data resources, storage medium and electronic equipment | |
| CN114861889B (en) | Deep learning model training method, target object detection method and device | |
| WO2023024975A1 (en) | Text processing method and apparatus, and electronic device | |
| CN111339295A (en) | Method, apparatus, electronic device and computer readable medium for presenting information | |
| JP7140913B2 (en) | Video distribution statute of limitations determination method and device | |
| CN111414471B (en) | Method and device for outputting information | |
| CN110245334B (en) | Method and device for outputting information | |
| CN111555960A (en) | Method for generating information | |
| CN114298007A (en) | Text similarity determination method, device, equipment and medium | |
| CN112182255A (en) | Method and apparatus for storing media files and for retrieving media files | |
| CN108846098B (en) | Information flow abstract generating and displaying method | |
| CN113011169B (en) | Method, device, equipment and medium for processing conference summary | |
| KR102222637B1 (en) | Apparatus for analysis of emotion between users, interactive agent system using the same, terminal apparatus for analysis of emotion between users and method of the same | |
| CN111488450A (en) | Method and device for generating keyword library and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200818 |