Method, device, equipment and computer-readable medium for pushing information

Abstract

The present invention discloses a method, device, equipment and computer-readable medium for pushing information, and relates to the field of computer technology. A specific implementation of the method includes: establishing a user live message set based on user messages during a live broadcast; segmenting the user messages in the user live message set to obtain a segmentation set; summarizing the number of each segmentation according to the segmentation set, and updating the segmentation dictionary of the live broadcast; combining the segmentation dictionary and the scene in the live broadcast to push high-frequency segmentations. This implementation can improve the quality and efficiency of pushing information, and prevent the live broadcast host from missing the speeches of multiple users.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, equipment and computer-readable medium for pushing information. Background Art

[0002] With the development of Internet technology, more people are paying attention to online live streaming. The technology of live streaming with goods is becoming more and more popular and accepted by the public, and major platforms are also vigorously supporting the live streaming with goods business.

[0003] The entry threshold for live broadcasting is low. As long as you have certain electronic equipment, you can conduct live broadcasting. When conducting live broadcasting business, users often speak and ask questions. After the live broadcast host sees the questions on the electronic equipment, he will reply to the questions during the live broadcast, realizing the interaction between the live broadcast host and the users.

[0004] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art: However, due to the fact that users speak quickly and in large numbers, and the screen limitations of electronic devices, the speech of the previous user is often updated by the speech of the next user, resulting in the live broadcast host not seeing the speech of the previous user, which disappears on the screen. Furthermore, there is a technical problem of pushing too much information, causing the live broadcast host to miss the speeches of multiple users. Summary of the invention

[0005] In view of this, the embodiments of the present invention provide a method, apparatus, device and computer-readable medium for pushing information, which can improve the quality and efficiency of pushing information and prevent the live broadcast host from missing the speeches of multiple users.

[0006] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for pushing information is provided, comprising:

[0007] Establish a user live broadcast message collection based on user messages during the live broadcast;

[0008] word segmentation processing of the user messages in the user live broadcast message set to obtain a word segmentation set;

[0009] Summarize the number of each word segment according to the word segmentation set, and update the word segmentation dictionary of the live broadcast;

[0010] Combine the word segmentation dictionary and the live broadcast scene to push frequently appearing word segmentations.

[0011] The word segmentation process is to process the user messages in the user live message set to obtain a word segmentation set, including:

[0012] word segmentation processing of the interrogative sentence in the user's message in the user live message set to obtain the words of the interrogative sentence;

[0013] The words are taken as the word set.

[0014] The word segmentation process is to process the user messages in the user live message set to obtain a word segmentation set, including:

[0015] The maximum matching algorithm and / or the N-gram word segmentation algorithm are used to process the user messages in the user live broadcast message set to obtain a word segmentation set.

[0016] The word segmentation dictionary includes a word segmentation dictionary for the current live broadcast and / or a word segmentation dictionary for the historical live broadcast.

[0017] The word segmentation dictionary includes a word segmentation dictionary for the current live broadcast and a word segmentation dictionary for the historical live broadcast;

[0018] The combining of the word segmentation dictionary and pushing the frequently appearing word segmentations includes:

[0019] According to the high-frequency segmented words in the segmented word dictionary of the current live broadcast and the high-frequency segmented words in the segmented word dictionary of the historical live broadcast, the segmented words that appear frequently are determined and pushed.

[0020] Combining the word segmentation dictionary with the live broadcast scene to push frequently appearing word segmentations includes:

[0021] Combine the word segmentation dictionary with the keywords of the scene in the live broadcast and / or the time period of the scene in the live broadcast to push the frequently appearing word segmentations.

[0022] The frequently appearing participles in the push include:

[0023] The frequently appearing segmented words are pushed in a preset manner, wherein the preset manner is included in the live broadcast interface and / or in the preset software.

[0024] According to a second aspect of an embodiment of the present invention, there is provided a device for pushing information, including:

[0025] A message module, used to establish a user live message collection based on user messages during the live broadcast;

[0026] A word segmentation module, used for word segmentation processing of user messages in the user live broadcast message set to obtain a word segmentation set;

[0027] An updating module, used for summarizing the quantity of each segmentation according to the segmentation set, and updating the segmentation dictionary of the live broadcast;

[0028] The push module is used to push frequently appearing segmented words in combination with the segmented word dictionary.

[0029] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for pushing information, including:

[0030] one or more processors;

[0031] a storage device for storing one or more programs,

[0032] When the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0033] According to a fourth aspect of an embodiment of the present invention, there is provided a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the method as described above is implemented.

[0034] One embodiment of the above invention has the following advantages or beneficial effects: establishing a user live message set based on user messages during the live broadcast; processing the user messages in the user live message set by word segmentation to obtain a word segmentation set; summarizing the number of each word segmentation according to the word segmentation set, and updating the live broadcast word segmentation dictionary; combining the word segmentation dictionary and the scene in the live broadcast to push frequently appearing word segments. The pushed word segments are determined based on the user live messages, thereby improving the quality and efficiency of the pushed information and preventing the live broadcast host from missing the speeches of multiple users.

[0035] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0037] Figure 1 is a schematic diagram of the main process of the method for pushing information according to an embodiment of the present invention;

[0038] Figure 2 is a schematic diagram of a process of obtaining a word segmentation set according to an embodiment of the present invention;

[0039] Figure 3 is a schematic diagram of a process of obtaining words of a question sentence according to an embodiment of the present invention;

[0040] Figure 4 is a schematic diagram of a process of pushing information according to an embodiment of the present invention;

[0041] Figure 5 is a schematic diagram of the main structure of an apparatus for pushing information according to an embodiment of the present invention;

[0042] Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0043] Figure 7 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0045] Currently, during a live broadcast, the host can only see user messages by checking the screen at any time. However, due to the fast and frequent speeches of users and the limitations of the electronic device screen, the speech of the previous user is often updated by the speech of the next user. As an example, the screen can only display 10 lines of subtitles. User A's speech occupies 3 lines, user B's speech occupies 4 lines, and user C's speech occupies 3 lines. At this time, the 10 lines of subtitles on the screen are completely occupied. User D's speech occupies 2 lines. In order to display user D's speech, the first two lines of user A's speech are deleted.

[0046] As a result, the host of the live broadcast did not see the speech of the previous user, and the speech disappeared on the screen. Therefore, there is a technical problem of pushing too much information, causing the host of the live broadcast to miss the speeches of multiple users.

[0047] In order to solve the technical problem of pushing too much information, the following technical solution in the embodiment of the present invention can be adopted.

[0048] See also Figure 1 , Figure 1 Schematic diagram of the main process of the method for pushing information according to an embodiment of the present invention, word segmentation processing of question sentences in user messages, and pushing high-frequency words in question sentences. Figure 1 As shown, the specific steps include:

[0049] S101. Establish a user live broadcast message collection based on user messages during the live broadcast process.

[0050] In the era of mobile Internet, text, pictures and videos can all be used for live broadcast. During the live broadcast, the host can interact with users in real time. Specifically, the host introduces the product, and the user sends a message on the live broadcast interface. The host gives a detailed explanation of the user's message, and then forms a real-time interaction between the host and the user.

[0051] The host of the live broadcast browses the user messages on the live broadcast interface to achieve online real-time interaction with the users. However, when there are many user messages, one user message is often updated by another user message, making it difficult for the host of the live broadcast to see all the user messages.

[0052] In order to facilitate the live broadcast host to obtain as many effective user messages as possible in a timely manner, it is first necessary to establish a user live broadcast message set. The user live broadcast message set is the sum of user messages during the live broadcast process. That is, the user live broadcast message set is established based on the user messages during the live broadcast process.

[0053] In one embodiment of the present invention, the user live message set is the sum of user messages during the current live broadcast. With the end of the current live broadcast, the number of user messages in the user live message set is fixed. The user live message set can meet the interaction between the live broadcast and the user.

[0054] In one embodiment of the present invention, the user live message set is the sum of the user messages in the current live broadcast process and the user messages in the historical live broadcast process. That is, as the number of live broadcasts increases, the number of user messages in the user live message set increases accordingly. By using the user live message set, it is possible to interact with the user from a longer time period, based on the historical live broadcast and the current live broadcast, to achieve interaction with the user.

[0055] S102: Process the user messages in the user live broadcast message set by word segmentation to obtain a word segmentation set.

[0056] In the process of implementing the embodiment of the present invention, the user messages in the user live message set can reflect the interactive content. Then, the user messages in the user live message set are processed by word segmentation to obtain a word segmentation set. The word segmentation set includes words in multiple user messages.

[0057] See also Figure 2 , Figure 2 1 is a flow chart of obtaining a word segmentation set according to an embodiment of the present invention, which specifically includes the following steps:

[0058] Through many practices, we know that interrogative sentences can fully represent the content that users need the live host to reply to. Therefore, it is necessary to process interrogative sentences in user messages in the user live message set.

[0059] S201, word segmentation processing of question sentences in user live broadcast message collection, to obtain words of the question sentences.

[0060] First, interrogative sentences are selected from the user live broadcast message collection, and then the words of the interrogative sentences are obtained.

[0061] See also Figure 3 , Figure 3 1 is a flow chart of obtaining words of a question sentence according to an embodiment of the present invention, which specifically includes the following steps:

[0062] S301. Use regular expressions to filter out interrogative sentences from a collection of user live broadcast messages.

[0063] The types of interrogative sentences are mainly divided into yes-no questions, wh-questions, alternative questions, and positive-negative questions. Each type of interrogative sentence has specific words. Use regular expressions to determine whether there are the following specific words in each user message, and then determine whether the user message is an interrogative sentence. As an example, the specific words include: "ma", "what", "is", "or", "go out", "not go out", etc.

[0064] Yes-no question: Did you go to work this morning?

[0065] Wh-question: What did you eat today?

[0066] Alternative question: Should we go to the cafeteria or a restaurant today?

[0067] Positive-negative question: Are we going out to eat today?

[0068] That is to say, use regular expressions to filter out interrogative sentences in the set of user live messages.

[0069] S302. Perform word segmentation on the interrogative sentences to obtain the words of the interrogative sentences.

[0070] An interrogative sentence includes multiple words. In order to obtain the words of each interrogative sentence, it is necessary to perform word segmentation on the interrogative sentences in the set of user live messages to obtain the words in the interrogative sentences.

[0071] In an embodiment of the present invention, the maximum matching algorithm and / or the N-gram word segmentation algorithm are used for word segmentation. The maximum matching algorithm is a relatively simple word segmentation method, which has a fast word segmentation speed and good effect for the live application scenario. The N-gram word segmentation algorithm can also be used, as well as the maximum matching algorithm and the N-gram word segmentation algorithm for word segmentation.

[0072] In Figure 3 In the embodiment, regular expressions are used to filter out interrogative sentences, and after word segmentation of the interrogative sentences, the words of the interrogative sentences are obtained.

[0073] S202. Use the words as a word segmentation set.

[0074] Use the words of the interrogative sentences as a word segmentation set. It can be understood that the word segmentation set includes the words of the interrogative sentences. The above interrogative sentences are from the set of user live messages.

[0075] In Figure 2 In the embodiment, word segmentation is performed on the interrogative sentences in the set of user live messages, and then a word segmentation set is obtained.

[0076] S103. Summarize the quantity of each word according to the word segmentation set, and update the word segmentation dictionary of the live broadcast.

[0077] The word segmentation set includes the word segmentation of user messages. During the live broadcast, user messages are not completely consistent, but they may be messages with the same substantive content. Summarize the word segmentation of user messages to obtain the number of each word segmentation. Determine the consistency of user messages by word segmentation.

[0078] As an example, user message 1 includes segmentation a and segmentation b; user message 2 includes segmentation a, segmentation b, and segmentation c. Segmentation a, segmentation b, and segmentation c belong to a segmentation set. According to the segmentation set summary, the number of segmentation a is 2, the number of segmentation b is 1, and the number of segmentation c is 1.

[0079] That is to say, the number of segmented words in the segmented word set needs to be summarized, and the live segmented word dictionary is updated with the number of segmented words.

[0080] In the embodiment of the present invention, the word segmentation dictionary is distinguished by the identifier of the live broadcast. As an example, the identifier of the live broadcast may be the identifier of the live broadcast host.

[0081] That is to say, one live broadcast corresponds to one word segmentation dictionary. After summarizing the number of each word segmentation, the word segmentation and the number of word segmentations are saved in the word segmentation dictionary as key-value pairs. As an example, the word segmentation is used as the key and the number of word segmentations is used as the value.

[0082] In one embodiment of the present invention, the word segmentation dictionary includes a word segmentation dictionary for the current live broadcast and / or a word segmentation dictionary for the historical live broadcast.

[0083] The word segmentation dictionary of the current live broadcast is the word segmentation dictionary involved in the current live broadcast. As an example, the live broadcast time of the current live broadcast is 12:00 to 13:00, and the word segmentation dictionary established for the user messages during the current live broadcast is the word segmentation dictionary of the current live broadcast.

[0084] The word segmentation dictionary of the historical live broadcast is the word segmentation dictionary involved in multiple live broadcasts. It can also be understood that the word segmentation dictionary of the historical live broadcast includes the word segmentations involved in the historical live broadcast.

[0085] S104: Push frequently appearing segmented words based on the segmentation dictionary and the live broadcast scene.

[0086] Arrange the words in the word segmentation dictionary in descending order, take the first N words as the high-frequency words, combine them with the live broadcast scene, and push the high-frequency words. N is a preset parameter greater than 1.

[0087] Combined with the word segmentation dictionary of the current live broadcast, the frequently appearing words pushed can fully reflect the content that users expect to interact with in the current live broadcast. Combined with the word segmentation dictionary of the historical live broadcast, the frequently appearing words pushed can interact with the content that most users care about. As an example, when users leave few messages, the word segmentation dictionary of the historical live broadcast can be used to push frequently appearing words.

[0088] In one embodiment of the present invention, the word segmentation dictionary includes a word segmentation dictionary for the current live broadcast and a word segmentation dictionary for the historical live broadcast. It is understandable that the frequently appearing word segmentation dictionary may belong to the word segmentation dictionary for the current live broadcast or the word segmentation dictionary for the historical live broadcast.

[0089] As an example, if there are few messages from users in the current live broadcast, the word segmentation dictionary of the historical live broadcast can be used to push the frequently appearing word segmentations. This is because users often have the same questions as previous users. If there are many messages from users in the current live broadcast, the word segmentation dictionary of the current live broadcast can be used to specifically meet the interaction needs of the current users. That is, based on the high-frequency word segmentations in the word segmentation dictionary of the current live broadcast and the high-frequency word segmentations in the word segmentation dictionary of the historical live broadcast, the frequently appearing word segmentations are determined and pushed.

[0090] In one embodiment of the present invention, a variety of scenarios are involved in the live broadcast process. The scenarios are commodities and / or events involved in the live broadcast. As an example, commodity A and commodity B are sold during the live broadcast process. As another example, event 1 and event 2 occur during the live broadcast process.

[0091] The scenes in the live broadcast can be identified by keywords and / or time periods. As an example, the name of product A is used as a keyword to identify the sale of product A, and the name of product B is used as a keyword to identify the sale of product B. As another example, 9:00 to 9:30 is used to identify the sale of product A, and 9:30 to 10:00 is used to identify the sale of product B.

[0092] That is to say, the segmented words that appear frequently are pushed by combining the segmented word dictionary with the keywords of the scene in the live broadcast and / or the time period of the scene in the live broadcast. In this way, the relationship between the live broadcast scene and the pushed segmented words can be fully considered, and the pushed segmented words are more targeted.

[0093] In one embodiment of the present invention, there are multiple ways to push frequently appearing segmented words. Specifically, the frequently appearing segmented words are pushed in a preset way, and the preset way is included in the live broadcast interface and / or in the preset software.

[0094] As an example, the live host can see not only user messages but also frequently occurring segmented words in the live interface. In this way, the live host can interact with the user in real time based on the user messages and frequently occurring segmented words during the live broadcast.

[0095] As another example, considering the limited physical size of the screen, the high-frequency segmented words displayed in the live broadcast interface are limited. The high-frequency segmented words can be pushed in the preset software. For example, the high-frequency segmented words are displayed in the software aa. Among them, the high-frequency segmented words are pushed to the software aa, and the live broadcast host can browse the high-frequency segmented words displayed in the software aa through other electronic devices.

[0096] In the above-mentioned embodiment of the present invention, a user live message set is established based on user messages during the live broadcast process; user messages in the user live message set are processed by word segmentation to obtain a word segmentation set; the number of each word segmentation is summarized according to the word segmentation set, and the live broadcast word segmentation dictionary is updated; and the word segmentation dictionary and the live broadcast scene are combined to push the frequently appearing words. The word segmentation pushed to the live broadcast host is determined based on the user live message, thereby improving the quality and efficiency of the pushed information and preventing the live broadcast host from missing the speeches of multiple users.

[0097] See also Figure 4 , Figure 4 Schematic diagram of the process of pushing information according to an embodiment of the present invention, which specifically includes the following steps:

[0098] S401. Collect user messages and create a user live broadcast message collection.

[0099] When the live broadcast host is selling mobile phones, all user messages are automatically collected and saved in the user live broadcast message collection, marked with D.

[0100] S402, filtering the user live broadcast message collection and retaining the question sentences.

[0101] The user messages in the user live message set D are screened, and the question sentences therein are extracted using regular expressions and stored in another set list, marked with T.

[0102] As an example, the T set includes the following interrogative sentences: 1. What material is this phone made of? 2. What is the resolution of the phone? 3. What are the colors? 4. Does it have NFC? 5. How long is the battery life? 6. What is the battery capacity? 7. Is the phone clear for watching movies? 8. Does it come with headphones? 9. How big is the phone? 10. How is the camera? 11. Is the photo clear? 12. Whose processor is it? 13. Is it a Qualcomm processor? 14. Is it an MTK processor?

[0103] S403, using the maximum matching algorithm to segment the question sentence.

[0104] The question sentences in the T set are segmented using the maximum matching algorithm to obtain multiple segmentations of the question sentences.

[0105] S404: The word segmentation results are stored in a word segmentation set.

[0106] The multiple segmentations of the question sentence are taken as segmentation results and saved in a segmentation set, marked with F.

[0107] S405: traverse the segmentations in the segmentation set, and save the segmentations and the number of segmentations.

[0108] Traverse the word set F, compare each word, count the number of identical words, and save the words and their numbers in the live host's word dictionary in the form of key-value, marked here by M.

[0109] S406. Sort by the number of participles from large to small.

[0110] Sort M by word segmentation data from most to least.

[0111] S407: Push the top 10 word segmentations.

[0112] Get the top 10 word segments and push them to the live host on the live broadcast page for their reference.

[0113] As an example, after the problem in S402 is processed, the following word segments are pushed: 1. Resolution; 2. Processor; 3. Battery size; 4. Material; 5. Color type; 6. NFC; 7. Whether to provide headphones; 8. Phone size.

[0114] In the above embodiment, the computer processes the data quickly, which can reach the millisecond level. Generally, the data volume of tens of millions can be processed quickly to ensure the real-time performance of the word segmentation push.

[0115] See also Figure 5 , Figure 5 is a schematic diagram of the main structure of the device for pushing information according to an embodiment of the present invention. The device for pushing information can implement a method for pushing information, such as Figure 5 As shown, the device for pushing information specifically includes:

[0116] Message module 501, used to establish a user live message collection based on user messages during the live broadcast process;

[0117] A word segmentation module 502, configured to process the user messages in the user live message set by word segmentation to obtain a word segmentation set;

[0118] An updating module 503, configured to summarize the number of each segmentation according to the segmentation set, and update the segmentation dictionary of the live broadcast;

[0119] The push module 504 is used to push frequently appearing segmented words in combination with the segmented word dictionary and the live broadcast scene.

[0120] In one embodiment of the present invention, the word segmentation module 502 is specifically used to process the interrogative sentences in the user's live broadcast message set by word segmentation to obtain the words of the interrogative sentences;

[0121] The words are taken as the word set.

[0122] In one embodiment of the present invention, the word segmentation module 502 is specifically used to use a maximum matching algorithm and / or an N-gram word segmentation algorithm to process the user messages in the user live broadcast message set to obtain a word segmentation set.

[0123] In one embodiment of the present invention, the word segmentation dictionary includes a word segmentation dictionary for the current live broadcast and / or a word segmentation dictionary for the historical live broadcast.

[0124] In one embodiment of the present invention, the word segmentation dictionary includes a word segmentation dictionary for the current live broadcast and a word segmentation dictionary for the historical live broadcast;

[0125] The push module 504 is specifically used to determine and push frequently appearing segmented words according to the high-frequency segmented words in the segmented word dictionary of the current live broadcast and the high-frequency segmented words in the segmented word dictionary of the historical live broadcast.

[0126] In one embodiment of the present invention, the push module 504 is specifically used to push frequently appearing segmented words in combination with the segmented word dictionary and the keywords of the scene in the live broadcast and / or the time period of the scene in the live broadcast.

[0127] In one embodiment of the present invention, the push module 504 is specifically used to push frequently appearing segmented words in a preset manner, and the preset manner is included in the live broadcast interface and / or in the preset software.

[0128] Figure 6 An exemplary system architecture 600 is shown to which the method for pushing information or the apparatus for pushing information according to the embodiments of the present invention can be applied.

[0129] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0130] Users can use terminal devices 601, 602, and 603 to interact with server 605 through network 604 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 601, 602, and 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0131] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0132] The server 605 may be a server that provides various services, such as a backend management server (only an example) that provides support for shopping websites browsed by users using the terminal devices 601, 602, and 603. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0133] It should be noted that the method for pushing information provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the device for pushing information is generally set in the server 605 .

[0134] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0135] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of a terminal device suitable for implementing an embodiment of the present invention. Figure 7 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0136] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0137] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0138] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present invention are executed.

[0139] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0140] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0141] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, they may be described as: a processor including a message module, a word segmentation module, an update module, and a push module. The names of these modules do not, in some cases, constitute limitations on the modules themselves. For example, the message module may also be described as "used to establish a user live message collection based on user messages during the live broadcast process."

[0142] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes:

[0143] Establish a user live broadcast message collection based on user messages during the live broadcast;

[0144] word segmentation processing of the user messages in the user live broadcast message set to obtain a word segmentation set;

[0145] Summarize the number of each word segment according to the word segmentation set, and update the word segmentation dictionary of the live broadcast;

[0146] Combine the word segmentation dictionary and the live broadcast scene to push frequently appearing word segmentations.

[0147] According to the technical solution of the embodiment of the present invention, a user live message set is established based on the user messages during the live broadcast process; the user messages in the user live message set are processed by word segmentation to obtain a word segmentation set; the number of each word segmentation is summarized according to the word segmentation set, and the live broadcast word segmentation dictionary is updated; the word segmentation dictionary and the scene in the live broadcast are combined to push the frequently appearing words. The word segmentation pushed to the live broadcast host is determined based on the user live message, thereby improving the quality and efficiency of the pushed information and preventing the live broadcast host from missing the speeches of multiple users.

[0148] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for pushing information, characterized in that: include: Establishing a user live broadcast message set based on user messages during the live broadcast process, wherein the user live broadcast message set is the sum of user messages during the current live broadcast process; word segmentation processing of the user messages in the user live broadcast message set to obtain a word segmentation set; Summarize the number of each word segment according to the word segmentation set, and update the word segmentation dictionary of the live broadcast; Combining the word segmentation dictionary and the live broadcast scene, push the frequently appearing word segmentations; The word segmentation process is to process the user messages in the user live message set to obtain a word segmentation set, including: word segmentation processing of the interrogative sentence in the user's message in the user live message set to obtain the words of the interrogative sentence; Taking the words as the word set; The combining of the word segmentation dictionary and the live broadcast scene to push frequently appearing word segmentations includes: Combine the word segmentation dictionary with the keywords of the scene in the live broadcast and / or the time period of the scene in the live broadcast to push the frequently appearing word segmentations.

2. The method for pushing information according to claim 1, characterized in that: The word segmentation process is to process the user messages in the user live message set to obtain a word segmentation set, including: The maximum matching algorithm and / or the N-gram word segmentation algorithm are used to process the user messages in the user live broadcast message set to obtain a word segmentation set.

3. The method for pushing information according to claim 1, characterized in that: The word segmentation dictionary includes a word segmentation dictionary for the current live broadcast and / or a word segmentation dictionary for the historical live broadcast.

4. The method for pushing information according to claim 1, characterized in that: The word segmentation dictionary includes a word segmentation dictionary for the current live broadcast and a word segmentation dictionary for the historical live broadcast; The step of combining the word segmentation dictionary and pushing the frequently appearing word segmentations includes: According to the high-frequency segmented words in the segmented word dictionary of the current live broadcast and the high-frequency segmented words in the segmented word dictionary of the historical live broadcast, the segmented words that appear frequently are determined and pushed.

5. The method for pushing information according to any one of claims 1 to 4, characterized in that: The frequently appearing participles in the push include: The frequently appearing segmented words are pushed in a preset manner, wherein the preset manner is included in the live broadcast interface and / or in the preset software.

6. A device for pushing information, characterized in that: include: A message module, used to establish a user live message set based on user messages during the live broadcast process, wherein the user live message set is the sum of user messages during the current live broadcast process; A word segmentation module, used for word segmentation processing of user messages in the user live broadcast message set to obtain a word segmentation set; And, word segmentation processing of the interrogative sentences in the user's live broadcast message set to obtain the words of the interrogative sentences; and using the words as the word segmentation set; An updating module, used for summarizing the quantity of each segmentation according to the segmentation set, and updating the segmentation dictionary of the live broadcast; The push module is used to push frequently appearing segmented words in combination with the segmented word dictionary; and to push frequently appearing segmented words in combination with the segmented word dictionary and the keywords of the scene in the live broadcast and / or the time period of the scene in the live broadcast.

7. An electronic device for pushing information, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.

8. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images