WO2020181783A1 - 用于发送信息的方法和装置 - Google Patents

用于发送信息的方法和装置 Download PDF

Info

Publication number
WO2020181783A1
WO2020181783A1 PCT/CN2019/113903 CN2019113903W WO2020181783A1 WO 2020181783 A1 WO2020181783 A1 WO 2020181783A1 CN 2019113903 W CN2019113903 W CN 2019113903W WO 2020181783 A1 WO2020181783 A1 WO 2020181783A1
Authority
WO
WIPO (PCT)
Prior art keywords
user terminal
image
expression image
target
emoticon
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.)
Ceased
Application number
PCT/CN2019/113903
Other languages
English (en)
French (fr)
Inventor
田飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Baidu Online Network Technology Beijing Co Ltd
Original Assignee
Baidu Online Network Technology Beijing Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Baidu Online Network Technology Beijing Co Ltd filed Critical Baidu Online Network Technology Beijing Co Ltd
Publication of WO2020181783A1 publication Critical patent/WO2020181783A1/zh
Priority to US17/118,588 priority Critical patent/US11706172B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

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
    • H04L51/10—Multimedia information
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/164—Detection; Localisation; Normalisation using holistic features
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/174—Facial expression recognition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • 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]

Definitions

  • the embodiments of the present disclosure relate to the field of computer technology, in particular to methods and devices for sending information.
  • the present disclosure proposes methods and devices for sending information.
  • an embodiment of the present disclosure provides a method for sending information.
  • the method includes: acquiring user input information input by a user to a user terminal; from a set of target expression images, determining to be sent to the user terminal and interacting with At least one emoticon image that matches the user input information, and the presentation order of the at least one emoticon image; in response to determining that the number of times the user terminal has presented at least one emoticon image in the presentation order in the historical time period is less than or equal to the target number of times, the user The terminal sends presentation information, where the presentation information is used to instruct the user terminal to present at least one emoticon image in the presentation order determined above.
  • determining at least one expression image to be sent to the user terminal and having the same category as the acquired expression image includes: from the target expression image collection, determining the same as the acquired expression image The emoticon image subsets of the same category belong to; from the emoticon image subset, select at least one emoticon image to be sent to the user terminal.
  • determining the expression image subset with the same category as the obtained expression image belongs to includes: inputting the obtained expression image to a pre-trained deep neural network to obtain The category to which the obtained facial expression image belongs; from the target facial expression image collection, a subset of facial expression images belonging to the obtained category is searched.
  • the method further includes: in response to a preset time elapsed from the last generation time of the target expression image set, updating the target expression image set to generate a new target expression image set; and from the target expression image set, Determining at least one emoticon image to be sent to the user terminal and matching user input information includes: determining at least one emoticon to be sent to the user terminal and matching user input information from a set of target emoticon images obtained in the last update image.
  • the target number of times is zero.
  • obtaining user input information input by the user to the user terminal includes: obtaining user input information input by the user to the user terminal and not sent to other user terminals except the user terminal.
  • an embodiment of the present disclosure provides an apparatus for sending information.
  • the apparatus includes: an obtaining unit configured to obtain user input information input by a user to a user terminal; and a determining unit configured to obtain information from a target expression In the image set, determine at least one emoticon image to be sent to the user terminal and match the user input information, and the presentation order of the at least one emoticon image; the sending unit is configured to respond to determining that the user terminal is in the historical time period according to The number of times the at least one emoticon image is presented in the presentation sequence is less than or equal to the target number of times, and the presentation information is sent to the user terminal, where the presentation information is used to instruct the user terminal to present the at least one emoticon image in the presentation order determined above.
  • the user input information is an emoticon image
  • the determining unit includes: a first determining subunit configured to determine from the target emoticon image set to be sent to the user terminal and to which the acquired emoticon image belongs At least one emoticon image of the same category is used as at least one emoticon image matching the user input information.
  • the first determining subunit includes: a determining module configured to determine from a set of target expression images, a subset of expression images in the same category as the acquired expression image belongs; a selection module configured to From the emoticon image subset, select at least one emoticon image to be sent to the user terminal.
  • the determining module includes: an input sub-module configured to input the acquired expression image to a pre-trained deep neural network to obtain the category to which the acquired expression image belongs; and the search sub-module configured to From the target emoticon image collection, find a subset of emoticon images belonging to the obtained category.
  • the device further includes: an update unit configured to update the target expression image set to generate a new target expression image set in response to a preset time elapsed from the last generation time of the target expression image set; and determine The unit includes: a second determining subunit configured to determine at least one emoticon image to be sent to the user terminal and matching the user input information from the target emoticon image set obtained by the latest update.
  • the target number of times is zero.
  • the obtaining unit includes: an obtaining subunit configured to obtain user input information input by the user to the user terminal and not sent to other user terminals except the user terminal.
  • the embodiments of the present disclosure provide a server for sending information, including: one or more processors; a storage device, on which one or more programs are stored, when the above one or more programs are The foregoing one or more processors execute, so that the one or more processors implement the method in any one of the foregoing methods for sending information.
  • the embodiments of the present disclosure provide a computer-readable medium for sending information, on which a computer program is stored, and when the program is executed by a processor, it can implement any one of the above methods for sending information.
  • Example method
  • the method and device for sending information obtain the user input information input by the user to the user terminal, and then, from the target emoticon image collection, it is determined to be sent to the user terminal and matches the user input information At least one emoticon image and the presentation sequence of the at least one emoticon image, and finally, in response to determining that the number of times the user terminal has presented at least one emoticon image in the presentation sequence in the historical time period is less than or equal to the target number of times, the presentation is sent to the user terminal Information, where the presentation information is used to instruct the user terminal to present at least one emoticon image in the above-determined presentation order, thereby reducing the number of repetitions of emoticon images to be presented by the user terminal, and helping the user to more quickly find the previous
  • the sent expressions can realize faster expression reply. In addition, it can reduce the number of times that the user terminal requests the expression image from the server in the process of searching for the expression image, thereby reducing the occupation of network resources.
  • FIG. 1 is an exemplary system architecture diagram in which an embodiment of the present disclosure can be applied
  • Fig. 2 is a flowchart of an embodiment of a method for sending information according to the present disclosure
  • 3A-3C are schematic diagrams of an application scenario of the method for sending information according to the present disclosure.
  • FIG. 4 is a flowchart of another embodiment of a method for sending information according to the present disclosure.
  • Fig. 5 is a schematic structural diagram of an embodiment of an apparatus for sending information according to the present disclosure
  • Fig. 6 is a schematic structural diagram of a computer system of a server suitable for implementing embodiments of the present disclosure.
  • FIG. 1 shows an exemplary system architecture 100 of an embodiment of a method for sending information or an embodiment of an apparatus for sending information to which an embodiment of the present disclosure can be applied.
  • the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105.
  • the network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105.
  • the network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables.
  • the user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to send user input information, or to receive emoticon images.
  • Various communication client applications such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, and social platform software, can be installed on the terminal devices 101, 102, and 103.
  • the terminal devices 101, 102, and 103 may be hardware or software.
  • the terminal devices 101, 102, 103 can be various electronic devices that have a display screen and support web browsing, including but not limited to smart phones, tablet computers, e-book readers, and MP3 players (Moving Picture Experts Group). Audio Layer III, Motion Picture Experts compress standard audio layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Motion Picture Experts compress standard audio layer 4) Players, laptop portable computers and desktop computers, etc.
  • the terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, software or software modules used to provide distributed services), or as a single software or software module. There is no specific limitation here.
  • the server 105 may be a server that provides various services, for example, a back-end server that performs image filtering on the expression images to be displayed on the terminal devices 101, 102, and 103.
  • the background server may determine from the target emoticon image collection at least one emoticon image to be sent to the user terminal and matching the received user input information.
  • the method for sending information provided by the embodiments of the present disclosure is generally executed by the server 105, and correspondingly, the device for sending information is generally set in the server 105.
  • the server can be hardware or software.
  • the server can be implemented as a distributed server cluster composed of multiple servers, or as a single server.
  • the server is software, it can be implemented as multiple software or software modules (for example, software or software modules for providing distributed services), or as a single software or software module. There is no specific limitation here.
  • the numbers of terminal devices, networks, and servers in FIG. 1 are merely illustrative. According to implementation needs, there can be any number of terminal devices, networks and servers.
  • the system architecture may only include the electronic device (such as the server 105) on which the method for sending information runs on.
  • the method for sending information includes the following steps:
  • Step 201 Obtain user input information input by the user to the user terminal.
  • the executor of the method for sending information can access the user terminal (for example, the terminal devices 101, 102, 103 shown in FIG. 1) through a wired connection or a wireless connection. ) To obtain user input information input by the user to the user terminal.
  • the above-mentioned user terminal may be a terminal used by the above-mentioned user, and it may be communicatively connected with the above-mentioned execution subject.
  • the above-mentioned user input information may be various information input by the user to the above-mentioned user terminal.
  • the user input information may include, but is not limited to, at least one of the following: text information, voice information, image information (such as an emoticon image), and so on.
  • Step 202 Determine, from the target emoticon image set, at least one emoticon image to be sent to the user terminal and matching the user input information, and the presentation order of the at least one emoticon image.
  • the above-mentioned execution subject may determine, from the target expression image set, at least one expression image to be sent to the user terminal and matching the user input information obtained in step 201, and determine the presentation of the above-mentioned at least one expression image order.
  • the aforementioned target expression image collection may be a collection of a large number of expression images.
  • the target emoticon image collection may be a predetermined number (e.g., 10,000, 100,000) of emoticons sent by the user with the highest frequency among all emoticon images on the network within a predetermined historical time period (for example, 30 days, 7 days, etc.) Collection of images.
  • the emoticon image matching the user input information may be an emoticon image that includes keywords of the user input information.
  • the emoticon image matching the user input information may be an emoticon image including the text "haha”.
  • the emoticon image matching the user input information may also be an emoticon image of the same category as the user input information.
  • the above-mentioned execution subject may first perform emotion recognition on the user input information to determine the user's emotion, and determine the determined emotion as the category to which the user input information belongs. Then, the above-mentioned execution subject may select from the target expression image collection, The expression image belonging to the category is determined as the expression image matching the user input information.
  • the foregoing presentation sequence may be used to indicate the sequence of the presentation of the at least one emoticon image in the user terminal.
  • the execution subject may adopt multiple methods to determine the presentation order of the at least one expression image.
  • the above-mentioned execution subject may randomly determine the presentation order of the above-mentioned at least one expression image, thereby instructing the user terminal to randomly present each of the above-mentioned at least one expression image.
  • the execution subject may first determine the number of times each expression image in the at least one expression image is presented on the user terminal, so as to determine the ascending or descending order of the number of times as the presentation order of the at least one expression image.
  • Step 203 In response to determining that the number of times that the user terminal has presented at least one emoticon image in the order of presentation within the historical time period is less than or equal to the target number of times, sending presentation information to the user terminal.
  • the execution subject may send presentation information to the user terminal.
  • the presentation information is used to instruct the user terminal to present at least one emoticon image according to the presentation order determined in step 202 above.
  • the aforementioned historical time period may be a time period before the current time (for example, when the step 203 is started), or a time period within a predetermined time range before the current time (for example, within 30 days with the current time as the end point).
  • the above-mentioned execution subject or an electronic device (such as a user terminal) communicatively connected with the above-mentioned execution subject may record the sequence of the emoticon images presented by the user terminal before performing this step 203, so as to determine the history of the user terminal The number of times that at least one emoticon image is presented in the aforementioned order of presentation within a time period.
  • the foregoing presentation information may be used to instruct the user terminal to present at least one emoticon image according to the foregoing determined presentation order.
  • the target number of times is zero.
  • the above-mentioned execution subject can send to the user terminal presentation information for instructing the user terminal to present at least one emoticon image in a presentation sequence that has not been used in the historical time period.
  • the user terminal can use A new presentation sequence is used to present the above-mentioned at least one emoticon image, thereby avoiding repeated presentation of emoticon images on the user terminal, and helping the user to more quickly find emoticons that have not been sent before, thereby realizing faster emoticon responses.
  • the number of times that the user terminal has not presented at least one emoticon image in the foregoing presentation order in the historical time period is less than or equal to the target number of times, and the presentation information is sent to the user terminal.
  • the user input information is an emoticon image. Therefore, the above-mentioned execution subject may also perform the above-mentioned step 202 in the following manner: from the target expression image set, determine at least one expression image that is to be sent to the user terminal and is the same as the category to which the acquired expression image belongs, as At least one emoticon image matching the user input information.
  • the above-mentioned executive body can determine at least one emoticon image belonging to the category of "happy" from the target expression image set , As at least one emoticon image matching the user input.
  • the aforementioned target emoticon image set may include emoticon images of various categories.
  • the target emoticon image collection may include emoticon images in categories such as "happy", “sad", and "depressed”.
  • the above-mentioned execution subject may also use the following method to perform step 202: from the target expression image set, determine the expression image sub-type of the same category as the acquired expression image. set. Then, from the subset of expression images, select at least one expression image to be sent to the user terminal.
  • the above-mentioned execution subject may adopt various methods to select at least one expression image to be sent to the user terminal from the subset of expression images.
  • the above-mentioned execution subject may randomly select a predetermined number (for example, 9) of expression images from the subset of expression images as the expression images to be sent to the user terminal.
  • the above-mentioned execution subject may also select an expression image with a sending frequency (the number of times an expression image is sent in a unit time) higher than a preset frequency threshold from a subset of expression images as the expression image to be sent to the user terminal.
  • a sending frequency the number of times an expression image is sent in a unit time
  • determining an expression image subset of the same category as the obtained expression image belongs to includes: inputting the obtained expression image to a preset
  • the trained deep neural network obtains the category to which the obtained facial expression image belongs, and then, from the target facial expression image set, finds a subset of the facial expression image belonging to the obtained category.
  • the above-mentioned deep neural network can be used to determine the category to which the expression image belongs.
  • the above-mentioned deep neural network may be a model obtained by training an initial deep neural network model by using a machine learning method.
  • the technician can pre-set the category of each expression image in the target expression image set in order to find a subset of expression images belonging to the obtained category.
  • GAN Generative Adversarial Networks
  • the generation diversity of facial expression images is limited and blurry images are easily generated.
  • a deep neural network is used to classify facial expression images, so that from the target facial expression image collection, a subset of facial expression images belonging to the obtained category is found, which helps to directly search from the target facial expression image collection A clear image is produced.
  • the above-mentioned execution subject may also perform the following steps: in response to a preset time period from the last generation time of the target expression image set, update the target expression image set to generate a new target expression Image collection. Therefore, the foregoing determination of at least one emoticon image to be sent to the user terminal and matching user input information from the target emoticon image set may include: determining to be sent to the user from the target emoticon image set obtained by the most recent update Terminal and at least one emoticon image matching the user input information.
  • the above-mentioned execution subject may use a plurality of new expression images to update each expression image in the target expression image set, thereby obtaining a new target expression image set.
  • this optional implementation method can update the target emoticon image collection, thereby further reducing the number of repetitions of emoticon images to be presented on the user terminal, and helping the user to more quickly find emoticons that have not been sent before.
  • Faster expression reply in addition, can further reduce the number of times the user terminal requests the expression image from the server in the process of the user looking for the expression image, thereby further reducing the occupation of network resources.
  • obtaining user input information input by the user to the user terminal may include the following sub-steps: obtaining user input to the user terminal and not sending it to other user terminals other than the user terminal User input information.
  • the process of a user chatting in a chat software is usually: the first step is to input information (that is, the user inputs information) into the input box.
  • the second step click the send button to send the input information to the user terminal used by the user's chat partner.
  • the user input information in the above substeps may be the information presented in the above input box, that is, the information input by the user before clicking the send button. Therefore, this optional implementation manner can push the emoticon image for the user terminal before the user sends the user input information to the user terminal indicated by the user's chat object, thereby improving the timeliness of image push.
  • FIGS. 3A to 3C are schematic diagrams of an application scenario of the method for sending information according to this embodiment.
  • the user inputs user input information 302 to the user terminal 301 (illustrated as an emoticon image in the category "smile").
  • the server 303 obtains the user input information 302 from the user terminal 301.
  • the server 303 determines from the target emoticon image collection 304, at least one emoticon image 305 to be sent to the user terminal 301 and matching the user input information 302, and the presentation order of the at least one emoticon image 305 ( For example, the presentation order of random presentation), and then, the server 303 determines that the number of times the user terminal 301 presents at least one emoticon image 305 in the above presentation order in the historical time period (for example, 30 days) is less than or equal to the target number of times (for example, 10), Thus, the server 303 transmits the presence information 306 to the user terminal 301.
  • the presentation information 306 is used to instruct the user terminal 301 to present at least one emoticon image 305 in a random presentation order. Please refer to FIG. 3C below.
  • the user terminal 301 presents at least one emoticon image 305 in a random presentation order.
  • one of the existing technologies is to present emoticon images to the user in the descending order of the frequency of using emoticon images when the user inputs user input information (such as text, emoticons, etc.) .
  • user input information such as text, emoticons, etc.
  • the user wants to find the emoticon images that he has not used before, or the emoticon that is used less frequently it will take more time to find it. This wastes the user's time on the one hand, and on the other hand, It may also require the number of times that the user terminal requests the emoticon image from the server, resulting in a large occupation of network resources. Therefore, in view of the above-mentioned problems, there is a need to push emoticon images that match the user input information input by the user and that are used less frequently.
  • the method provided by the above-mentioned embodiment of the present disclosure obtains user input information input by the user to the user terminal, and then, from the target expression image set, determines at least one expression image to be sent to the user terminal and matches the user input information, And the presentation order of at least one emoticon image. Finally, in the case that the number of times the at least one emoticon image is presented in the presentation sequence in the historical time period of the user terminal is less than or equal to the target number of times, the presentation information is sent to the user terminal so that the user The terminal presents at least one emoticon image in the order of presentation, thereby reducing the number of repetitions of emoticon images presented by the user terminal, and helping users to find expressions that have not been sent before, so as to achieve faster emoticon responses. In addition, It can reduce the number of times that the user terminal requests the emoticon image from the server in the process of searching for the emoticon image by the user, and reduces the occupation of network resources.
  • FIG. 4 shows a flow 400 of another embodiment of a method for sending information.
  • the process 400 of the method for sending information includes the following steps:
  • Step 401 Acquire an expression image input by the user to the user terminal. After that, step 402 is executed.
  • the executor of the method for sending information can access the user terminal (for example, the terminal devices 101, 102, 103 shown in FIG. 1) through a wired connection or a wireless connection. ) To obtain the facial expression image input by the user to the user terminal.
  • the above-mentioned user terminal may be a terminal used by the above-mentioned user, and it may be communicatively connected with the above-mentioned execution subject.
  • Step 402 Input the acquired expression image to a pre-trained deep neural network to obtain the category to which the acquired expression image belongs. After that, step 403 is executed.
  • the above-mentioned execution subject may input the expression image obtained in step 401 into a pre-trained deep neural network to obtain the category to which the obtained expression image belongs.
  • the above-mentioned deep neural network can be used to determine the category to which the expression image belongs.
  • the above-mentioned deep neural network may be a model obtained by training an initial deep neural network model by using a machine learning method.
  • Step 403 Acquire a set of target expression images. After that, step 404 is executed.
  • the above-mentioned execution subject may obtain a set of target expression images.
  • the aforementioned target expression image collection may be a collection of a large number of expression images.
  • the target emoticon image collection may be a predetermined number (e.g., 10,000, 100,000) of emoticons sent by the user with the highest frequency among all emoticon images on the network within a predetermined historical time period (for example, 30 days, 7 days, etc.) Collection of images.
  • Step 404 Determine whether a preset time period has passed since the last generation time of the target expression image set. After that, if yes, proceed to step 405; if not, proceed to step 406.
  • the above-mentioned execution subject may determine whether a preset time period has passed since the last generation time of the target expression image set.
  • Step 405 Update the target expression image set, and generate a new target expression image set. After that, step 403 is executed.
  • the above-mentioned execution subject may also update the target expression image set to generate a new target expression image set.
  • the target expression image set may be updated every preset time interval.
  • Step 406 Search for a subset of expression images belonging to the obtained category from the target expression image set obtained by the latest update. After that, step 407 is executed.
  • the above-mentioned execution subject may search for a subset of expression images belonging to the obtained category from the target expression image set obtained by the latest update.
  • the technician can pre-set the category of each expression image in the target expression image set in order to find a subset of expression images belonging to the obtained category.
  • Step 407 Select at least one emoticon image to be sent to the user terminal from the emoticon image subset. After that, step 408 is executed.
  • the above-mentioned execution subject may select at least one expression image to be sent to the user terminal from a subset of expression images.
  • the above-mentioned execution subject may adopt various methods to select at least one expression image to be sent to the user terminal from the subset of expression images.
  • the above-mentioned execution subject may randomly select a predetermined number (for example, 9) of expression images from the subset of expression images as the expression images to be sent to the user terminal.
  • the above-mentioned execution subject may also select an expression image with a sending frequency higher than a preset frequency threshold from the expression image subset as the expression image to be sent to the user terminal.
  • Step 408 Determine the presentation order of at least one emoticon image. After that, step 409 is executed.
  • the above-mentioned execution subject may determine the presentation order of at least one expression image.
  • the above-mentioned presentation sequence may be used to indicate the sequence of the above-mentioned at least one emoticon image when presented on the user terminal.
  • the execution subject may adopt multiple methods to determine the presentation order of the at least one expression image.
  • the execution subject may randomly determine the presentation order of the at least one expression image, so as to randomly present each expression image in the at least one expression image.
  • the execution subject may first determine the number of times each emoticon image in the at least one emoticon image is presented on the user terminal, so as to determine the ascending or descending order of the number of presentation times as the presentation order of the at least one emoticon image.
  • Step 409 In response to determining that the user terminal did not present at least one emoticon image in the foregoing presentation order within the historical time period, the presentation information is sent to the user terminal.
  • the above-mentioned execution subject may send presentation information to the user terminal when it is determined that the user terminal has not presented at least one emoticon image in the above-mentioned presentation sequence within the historical time period.
  • the presentation information is used to instruct the user terminal to present at least one emoticon image according to the foregoing determined presentation order.
  • steps 401 to 409 may also include the embodiment corresponding to FIG. 2 and the same features as the optional implementation manners, and produce the same effect.
  • the implementation of this application The examples are not repeated here.
  • the process 400 of the method for sending information in this embodiment highlights the use of a deep neural network to determine the expression image library (ie, the aforementioned target expression image set In ), the step of matching the emoticon image input by the user and to be sent to the user terminal.
  • the expression image library ie, the aforementioned target expression image set In
  • GAN Generative Adversarial Networks
  • a deep neural network is used to classify facial expression images, so that from the target facial expression image collection, a subset of facial expression images belonging to the obtained category is found, which helps to directly search from the target facial expression image collection A clear image is then sent to the user terminal.
  • the present disclosure provides an embodiment of a device for sending information.
  • the device embodiment corresponds to the method embodiment shown in FIG. 2, except In addition to the features described below, the device embodiment may also include the same or corresponding features as the method embodiment shown in FIG. 2.
  • the device can be applied to various electronic devices.
  • the apparatus 500 for sending information in this embodiment includes: an acquiring unit 501, a determining unit 502, and a sending unit 503.
  • the acquiring unit 501 is configured to acquire user input information input by the user to the user terminal
  • the determining unit 502 is configured to determine at least one emoticon image to be sent to the user terminal and matching the user input information from the target emoticon image set , And the presentation order of the at least one emoticon image
  • the sending unit 503 is configured to send presentation information to the user terminal in response to determining that the number of times the user terminal has presented the at least one emoticon image in the presentation order in the historical time period is less than or equal to the target number of times ,
  • the presentation information is used to instruct the user terminal to present at least one emoticon image in the presentation order determined above.
  • the acquiring unit 501 of the apparatus 500 for sending information can acquire user input from a user terminal (such as the terminal devices 101, 102, 103 shown in FIG. 1) through a wired connection or a wireless connection.
  • the user input information of the user terminal can be acquired from a user terminal (such as the terminal devices 101, 102, 103 shown in FIG. 1) through a wired connection or a wireless connection.
  • the above-mentioned user terminal may be a terminal used by the above-mentioned user, and it may be communicatively connected with the above-mentioned execution subject.
  • the above-mentioned user input information may be various information input by the user to the above-mentioned user terminal.
  • the user input information may include, but is not limited to, at least one of the following: text information, voice information, image information (such as an emoticon image), and so on.
  • the determining unit 502 may determine from the target expression image set at least one expression to be sent to the user terminal and matching the user input information obtained in step 201 Image, and determining the presentation order of the at least one emoticon image.
  • the aforementioned target expression image collection may be a collection of a large number of expression images.
  • the target emoticon image collection may be a predetermined number (e.g., 10,000, 100,000) of emoticons sent by the user with the highest frequency among all emoticon images on the network within a predetermined historical time period (for example, 30 days, 7 days, etc.) Collection of images.
  • the emoticon image matching the user input information may be an emoticon image that includes keywords of the user input information.
  • the foregoing presentation sequence may be used to indicate the sequence of the presentation of the at least one emoticon image in the user terminal.
  • the sending unit 503 may send presentation information to the user terminal.
  • the presentation information is used to instruct the user terminal to present at least one emoticon image according to the presentation order determined in step 202 above.
  • the aforementioned historical time period may be a time period before the current time (for example, when the step 203 is started), or a time period within a predetermined time range before the current time (for example, within 30 days with the current time as the end point).
  • the user input information is an expression image
  • the determining unit 502 includes: a first determining subunit (not shown in the figure) is configured to determine the target expression image set from the target expression image set. At least one emoticon image that is sent to the user terminal and belongs to the same category as the acquired emoticon image is used as at least one emoticon image that matches the user input information.
  • the first determining subunit includes: a determining module (not shown in the figure) is configured to determine from the target expression image set the category to which the acquired expression image belongs The same expression image subset; the selection module (not shown in the figure) is configured to select at least one expression image to be sent to the user terminal from the expression image subset.
  • the determining module includes: an input sub-module (not shown in the figure) configured to input the acquired expression image to a pre-trained deep neural network to obtain the acquired The category to which the expression image belongs; the search submodule (not shown in the figure) is configured to search for a subset of expression images belonging to the obtained category from the target expression image collection.
  • the device 500 further includes: an update unit (not shown in the figure) configured to update the target in response to a preset time elapsed from the last generation time of the target expression image set Expression image collection, generate a new target expression image collection.
  • the determining unit includes: a second determining subunit (not shown in the figure) is configured to determine at least one emoticon image to be sent to the user terminal and matching the user input information from the target emoticon image set obtained by the last update .
  • the target number of times is zero.
  • the acquiring unit includes: an acquiring subunit (not shown in the figure) configured to acquire user input to the user terminal and not send to other user terminals except the user terminal The user enters information.
  • the user input information input by the user to the user terminal is obtained through the obtaining unit 501, and then the determining unit 502 determines from the target expression image set to be sent to the user terminal and matches the user input information And the presentation order of at least one emoticon image.
  • the sending unit 503 responds to determining that the number of times the user terminal has presented at least one emoticon image in the order of presentation within the historical time period is less than or equal to the target number of times, and informs the user
  • the terminal sends presentation information, where the presentation information is used to instruct the user terminal to present at least one emoticon image in the presentation sequence determined above, thereby reducing the number of repetitions of emoticon images to be presented by the user terminal, and helping to facilitate the user more quickly It finds expressions that have not been sent before, thereby realizing faster expression responses.
  • it can also reduce the number of times the user terminal requests expression images from the server in the process of searching for expression images, reducing the occupation of network resources.
  • FIG. 6 shows a schematic structural diagram of a computer system 600 of a server suitable for implementing embodiments of the present disclosure.
  • the server shown in FIG. 6 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • the computer system 600 includes a central processing unit (CPU) 601, which can be based on a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603 And perform various appropriate actions and processing.
  • the RAM 603 also stores various programs and data required for the operation of the system 600.
  • the CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also connected to the bus 604.
  • the following components are connected to the I/O interface 605: an input part 606 including a keyboard, a mouse, etc.; an output part 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and speakers, etc.; a storage part 608 including a hard disk, etc. ; And a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet.
  • the driver 610 is also connected to the I/O interface 605 as needed.
  • a removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that the computer program read from it is installed into the storage part 608 as needed.
  • the process described above with reference to the flowchart can be implemented as a computer software program.
  • the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication section 609, and/or installed from the removable medium 611.
  • the central processing unit (CPU) 601 the above-mentioned functions defined in the method of the present disclosure are executed.
  • the computer-readable medium described in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable medium may send, propagate or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
  • the computer program code used to perform the operations of the present disclosure can be written in one or more programming languages or a combination thereof, the programming languages including object-oriented programming languages-such as Python, Java, Smalltalk, C++, and Including conventional procedural programming languages-such as "C" language or similar programming languages.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user’s computer through any kind of network including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider for example, using an Internet service provider to pass Internet connection.
  • each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logical function Executable instructions.
  • the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown in succession can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in the present disclosure can be implemented in software or hardware.
  • the described unit may also be provided in the processor.
  • a processor includes an acquiring unit, a determining unit, and a generating unit.
  • the names of these units do not constitute a limitation on the unit itself under certain circumstances.
  • the obtaining unit can also be described as "a unit for obtaining user input information input by the user to the user terminal".
  • the present disclosure also provides a computer-readable medium.
  • the computer-readable medium may be included in the server described in the above-mentioned embodiment; or may exist alone without being assembled into the server.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the server, the server: obtains user input information input by the user to the user terminal; At least one emoticon image that is sent to the user terminal and matches the user input information, and the presentation order of the at least one emoticon image; in response to determining that the user terminal has presented at least one emoticon image in the order of presentation within the historical time period, the number of times the at least one emoticon image is presented is less than It is equal to the target number of times, and the presentation information is sent to the user terminal, where the presentation information is used to instruct the user terminal to present at least one emoticon image in the presentation order determined above.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • User Interface Of Digital Computer (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Processing Or Creating Images (AREA)

Abstract

本公开的实施例公开了用于发送信息的方法和装置。该方法的一具体实施方式包括：获取输入至用户终端的用户输入信息；从目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，以及至少一个表情图像的呈现顺序；响应于确定用户终端在历史时间段内，按照呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数，向用户终端发送呈现信息，其中，呈现信息用于指示用户终端按照上述所确定出的呈现顺序呈现至少一个表情图像。该实施方式可以降低用户终端待呈现的表情图像的重复次数，有助于方便用户更快速查找到之前未发送过的表情，从而实现更快速的表情回复。

Description

用于发送信息的方法和装置
本专利申请要求于2019年03月08日提交的、申请号为201910175581.5、申请人为百度在线网络技术(北京)有限公司、发明名称为“用于发送信息的方法和装置”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。
技术领域
本公开的实施例涉及计算机技术领域，具体涉及用于发送信息的方法和装置。
背景技术
现有技术中，表情包数量庞大，用户往往需要在数量庞大的表情包集中，找出目标表情，从而进行发送等操作。而对于表情包的呈现而言，目前，用户使用频率越高的表情往往优先进行呈现或者呈现的位置较为靠前。
发明内容
本公开提出了用于发送信息的方法和装置。
第一方面，本公开的实施例提供了一种用于发送信息的方法，该方法包括：获取用户输入至用户终端的用户输入信息；从目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，以及至少一个表情图像的呈现顺序；响应于确定用户终端在历史时间段内，按照呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数，向用户终端发送呈现信息，其中，呈现信息用于指示用户终端按照上述所确定出的呈现顺序呈现至少一个表情图像。
在一些实施例中，用户输入信息为表情图像；以及从目标表情图 像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，包括：从目标表情图像集合中，确定待发送至用户终端并且与所获取到的表情图像所属的类别相同的至少一个表情图像，作为与用户输入信息相匹配的至少一个表情图像。
在一些实施例中，从目标表情图像集合中，确定待发送至用户终端并且与所获取到的表情图像的类别相同的至少一个表情图像，包括：从目标表情图像集合中，确定与所获取到的表情图像所属的类别相同的表情图像子集；从表情图像子集中，选择待发送至用户终端的至少一个表情图像。
在一些实施例中，从目标表情图像集合中，确定与所获取到的表情图像所属的类别相同的表情图像子集，包括：将所获取到的表情图像输入至预先训练的深度神经网络，获得所获取的表情图像所属的类别；从目标表情图像集合中，查找属于所获得的类别的表情图像子集。
在一些实施例中，该方法还包括：响应于距离目标表情图像集合的上次生成时间经过预设时长，更新目标表情图像集合，生成新的目标表情图像集合；以及从目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，包括：从最近一次更新得到的目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像。
在一些实施例中，目标次数为0。
在一些实施例中，获取用户输入至用户终端的用户输入信息，包括：获取用户输入至用户终端并且未发送至除用户终端之外的其他用户终端的用户输入信息。
第二方面，本公开的实施例提供了一种用于发送信息的装置，该装置包括：获取单元，被配置成获取用户输入至用户终端的用户输入信息；确定单元，被配置成从目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，以及至少一个表情图像的呈现顺序；发送单元，被配置成响应于确定用户终端在历史时间段内，按照呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数，向用户终端发送呈现信息，其中，呈现信息用于指示 用户终端按照上述所确定出的呈现顺序呈现至少一个表情图像。
在一些实施例中，用户输入信息为表情图像；以及确定单元包括：第一确定子单元，被配置成从目标表情图像集合中，确定待发送至用户终端并且与所获取到的表情图像所属的类别相同的至少一个表情图像，作为与用户输入信息相匹配的至少一个表情图像。
在一些实施例中，第一确定子单元包括：确定模块，被配置成从目标表情图像集合中，确定与所获取到的表情图像所属的类别相同的表情图像子集；选择模块，被配置成从表情图像子集中，选择待发送至用户终端的至少一个表情图像。
在一些实施例中，确定模块包括：输入子模块，被配置成将所获取到的表情图像输入至预先训练的深度神经网络，获得所获取的表情图像所属的类别；查找子模块，被配置成从目标表情图像集合中，查找属于所获得的类别的表情图像子集。
在一些实施例中，该装置还包括：更新单元，被配置成响应于距离目标表情图像集合的上次生成时间经过预设时长，更新目标表情图像集合，生成新的目标表情图像集合；以及确定单元包括：第二确定子单元，被配置成从最近一次更新得到的目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像。
在一些实施例中，目标次数为0。
在一些实施例中，获取单元包括：获取子单元，被配置成获取用户输入至用户终端并且未发送至除用户终端之外的其他用户终端的用户输入信息。
第三方面，本公开的实施例提供了一种用于发送信息的服务器，包括：一个或多个处理器；存储装置，其上存储有一个或多个程序，当上述一个或多个程序被上述一个或多个处理器执行，使得该一个或多个处理器实现如上述用于发送信息的方法中任一实施例的方法。
第四方面，本公开的实施例提供了一种用于发送信息的计算机可读介质，其上存储有计算机程序，该程序被处理器执行时实现如上述用于发送信息的方法中任一实施例的方法。
本公开的实施例提供的用于发送信息的方法和装置，通过获取用 户输入至用户终端的用户输入信息，然后，从目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，以及至少一个表情图像的呈现顺序，最后，响应于确定用户终端在历史时间段内，按照呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数，向用户终端发送呈现信息，其中，呈现信息用于指示用户终端按照上述所确定出的呈现顺序呈现至少一个表情图像，从而降低了用户终端待呈现的表情图像的重复次数，有助于方便用户更快速查找到之前未发送过的表情，从而实现更快速的表情回复，此外，还可以减少用户查找表情图像的过程中，用户终端向服务器请求表情图像的次数，由此可以减少对网络资源的占用。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本公开的其它特征、目的和优点将会变得更明显：
图1是本公开的一个实施例可以应用于其中的示例性系统架构图；
图2是根据本公开的用于发送信息的方法的一个实施例的流程图；
图3A-图3C是根据本公开的用于发送信息的方法的一个应用场景的示意图；
图4是根据本公开的用于发送信息的方法的又一个实施例的流程图；
图5是根据本公开的用于发送信息的装置的一个实施例的结构示意图；
图6是适于用来实现本公开的实施例的服务器的计算机系统的结构示意图。
具体实施方式
下面结合附图和实施例对本公开作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释相关发明，而非对该发 明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。
需要说明的是，在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本公开。
图1示出了可以应用本公开的实施例的用于发送信息的方法或用于发送信息的装置的实施例的示例性系统架构100。
如图1所示，系统架构100可以包括终端设备101、102、103，网络104和服务器105。网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
用户可以使用终端设备101、102、103通过网络104与服务器105交互，以发送用户输入信息，或者，接收表情图像等。终端设备101、102、103上可以安装有各种通讯客户端应用，例如网页浏览器应用、购物类应用、搜索类应用、即时通信工具、邮箱客户端、社交平台软件等。
终端设备101、102、103可以是硬件，也可以是软件。当终端设备101、102、103为硬件时，可以是具有显示屏并且支持网页浏览的各种电子设备，包括但不限于智能手机、平板电脑、电子书阅读器、MP3播放器(Moving Picture Experts Group Audio Layer III，动态影像专家压缩标准音频层面3)、MP4(Moving Picture Experts Group Audio Layer IV，动态影像专家压缩标准音频层面4)播放器、膝上型便携计算机和台式计算机等等。当终端设备101、102、103为软件时，可以安装在上述所列举的电子设备中。其可以实现成多个软件或软件模块(例如用来提供分布式服务的软件或软件模块)，也可以实现成单个软件或软件模块。在此不做具体限定。
服务器105可以是提供各种服务的服务器，例如对终端设备101、102、103上待显示的表情图像进行图像筛选的后台服务器。后台服务器可以从目标表情图像集合中，确定待发送至用户终端并且与其所接 收到的用户输入信息相匹配的至少一个表情图像。
需要说明的是，本公开的实施例所提供的用于发送信息的方法一般由服务器105执行，相应地，用于发送信息的装置一般设置于服务器105中。
需要说明的是，服务器可以是硬件，也可以是软件。当服务器为硬件时，可以实现成多个服务器组成的分布式服务器集群，也可以实现成单个服务器。当服务器为软件时，可以实现成多个软件或软件模块(例如用来提供分布式服务的软件或软件模块)，也可以实现成单个软件或软件模块。在此不做具体限定。
应该理解，图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、网络和服务器。当用于发送信息方法运行于其上的电子设备不需要与其他电子设备进行数据传输时，该系统架构可以仅包括用于发送信息方法运行于其上的电子设备(例如服务器105)。
继续参考图2，示出了根据本公开的用于发送信息的方法的一个实施例的流程200。该用于发送信息的方法，包括以下步骤：
步骤201，获取用户输入至用户终端的用户输入信息。
在本实施例中，用于发送信息的方法的执行主体(例如图1所示的服务器)可以通过有线连接方式或者无线连接方式从用户终端(例如图1所示的终端设备101、102、103)，获取用户输入至该用户终端的用户输入信息。
其中，上述用户终端可以是上述用户所使用的终端，其可以与上述执行主体通信连接。上述用户输入信息可以是用户向上述用户终端输入的各种信息。作为示例，该用户输入信息可以包括但不限于以下至少一项：文字信息、语音信息、图像信息(例如表情图像)等等。
步骤202，从目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，以及至少一个表情图像的呈现顺序。
在本实施例中，上述执行主体可以从目标表情图像集合中，确定 待发送至用户终端并且与步骤201获取到的用户输入信息相匹配的至少一个表情图像，以及确定上述至少一个表情图像的呈现顺序。
其中，上述目标表情图像集合可以是大量的表情图像的集合。作为示例，目标表情图像集合可以是预定历史时间段(例如30天、7天等等)内，网络上所有的表情图像中，被用户发送的频率最高的预定数量(例如10000、100000)张表情图像的集合。
与用户输入信息相匹配的表情图像，可以是包括用户输入信息的关键词的表情图像。作为示例，如果用户输入信息为“哈哈”，那么，与该用户输入信息相匹配的表情图像可以是包括文字“哈哈”的表情图像。可选的，与用户输入信息相匹配的表情图像，也可以是与用户输入信息所属的类别相同的表情图像。例如，上述执行主体可以首先对用户输入信息进行情绪识别，从而确定用户的情绪，并将所确定出的情绪确定为用户输入信息所属的类别，然后，上述执行主体可以从目标表情图像集合中，确定属于该类别的表情图像作为与用户输入信息相匹配的表情图像。
上述呈现顺序可以用于指示上述至少一个表情图像在用户终端进行呈现时的顺序。
在这里，上述执行主体可以采用多种方式，来确定上述至少一个表情图像的呈现顺序。
作为示例，上述执行主体可以随机确定上述至少一个表情图像的呈现顺序，从而指示用户终端随机呈现上述至少一个表情图像中的各个表情图像。
可选的，上述执行主体还可以首先确定上述至少一个表情图像中的各个表情图像在该用户终端的呈现次数，从而将呈现次数升序或者降序的顺序，确定为上述至少一个表情图像的呈现顺序。
步骤203，响应于确定用户终端在历史时间段内，按照呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数，向用户终端发送呈现信息。
在本实施例中，在确定用户终端在历史时间段内，按照上述呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数的情况 下，上述执行主体可以向用户终端发送呈现信息。其中，呈现信息用于指示用户终端按照上述步骤202所确定出的呈现顺序呈现至少上述一个表情图像。其中，上述历史时间段可以是当前时间(例如开始执行该步骤203时)之前的时间段，也可以是当前时间之前的预定时间范围内(例如以当前时间为终点的30天内)的时间段。
在这里，上述执行主体或者与上述执行主体通信连接的电子设备(例如用户终端)，在执行该步骤203之前，可以对用户终端呈现的表情图像的顺序进行记录，从而确定出用户终端在上述历史时间段内，按照上述呈现顺序对至少一个表情图像进行呈现的次数。
上述呈现信息可以用于指示用户终端按照上述所确定出的呈现顺序呈现至少一个表情图像。
上述目标次数可以是预先确定的次数(例如1、2)，也可以是采用上述历史时间段包括的数值，与预设数值的乘积。例如，如果历史时间段为“30天”，预设数值为“0.3”，那么，该历史时间段包括的数值为“30”，由此可得上述目标次数为“9”(9＝30×0.3)。
在本实施例的一些可选的实现方式中，目标次数为0。
可以理解，当目标次数为0时，上述执行主体可以向用户终端发送用于指示用户终端按照历史时间段内未采用过的呈现顺序，呈现至少一个表情图像的呈现信息，之后，用户终端可以采用一种新的呈现顺序，来呈现上述至少一个表情图像，从而避免了用户终端重复呈现表情图像，有助于方便用户更快速查找到之前未发送过的表情，从而实现更快速的表情回复。
在用户终端在历史时间段内未曾按照上述呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数，向用户终端发送呈现信息。
在本实施例的一些可选的实现方式中，用户输入信息为表情图像。由此，上述执行主体还可以采用如下方式来执行上述步骤202：从目标表情图像集合中，确定待发送至用户终端并且与所获取到的表情图像所属的类别相同的至少一个表情图像，作为与用户输入信息相匹配的至少一个表情图像。
作为示例，如果上述执行主体在步骤201获取到的表情图像所述 的类别为“高兴”，那么，上述执行主体可以从目标表情图像集合中，确定属于“高兴”这一类别的至少一个表情图像，作为与用户输入信息相匹配的至少一个表情图像。可以理解，上述目标表情图像集合中可以包括各个类别的表情图像。例如，目标表情图像集合可以包括“高兴”、“伤心”、“忧郁”等类别的表情图像。
在本实施例的一些可选的实现方式中，上述执行主体也可以采用如下方式，来执行步骤202：从目标表情图像集合中，确定与所获取到的表情图像所属的类别相同的表情图像子集。然后，从表情图像子集中，选择待发送至用户终端的至少一个表情图像。
在这里，上述执行主体可以采用多种方式，从表情图像子集中，选择待发送至用户终端的至少一个表情图像。
作为示例，上述执行主体可以从表情图像子集中，随机选择预定数量(例如9)个表情图像，作为待发送至用户终端的表情图像。
可选的，上述执行主体也可以从表情图像子集中，选择发送频率(单位时间内发送表情图像的次数)高于预设频率阈值的表情图像，作为待发送至用户终端的表情图像。
在本实施例的一些可选的实现方式中，从目标表情图像集合中，确定与所获取到的表情图像所属的类别相同的表情图像子集，包括：将所获取到的表情图像输入至预先训练的深度神经网络，获得所获取的表情图像所属的类别，然后，从目标表情图像集合中，查找属于所获得的类别的表情图像子集。
其中，上述深度神经网络可以用于确定表情图像所属的类别。作为示例，上述深度神经网络可以是采用机器学习方法，对初始深度神经网络模型进行训练而得到的模型。
在这里，技术人员可以预先设置目标表情图像集合中的每个表情图像的类别，以便查找属于所获得的类别的表情图像子集。
需要说明的是，现有技术之一为采用生成式对抗网络(Generative Adversarial Networks，GAN)，来生成表情图像，其表情图像的生成多样性有限，而且容易产生模糊的图像。而本可选的实现方式中采用深度神经网络来对表情图像进行分类，从而从目标表情图像集合中，查 找属于所获得的类别的表情图像子集，有助于直接从目标表情图像集合中查找出清晰的图像。
在本实施例的一些可选的实现方式中，上述执行主体还可以执行如下步骤：响应于距离目标表情图像集合的上次生成时间经过预设时长，更新目标表情图像集合，生成新的目标表情图像集合。由此，上述从目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，可以包括：从最近一次更新得到的目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像。
在这里，上述执行主体可以采用多个新的表情图像，来更新目标表情图像集合中的各个表情图像，从而得到新的目标表情图像集合。
可以理解，本可选的实现方式可以对目标表情图像集合进行更新，从而进一步降低了用户终端待呈现的表情图像的重复次数，有助于用户更快速查找到之前未发送过的表情，从而实现更快速的表情回复，此外，还可以进一步减少用户查找表情图像的过程中，用户终端向服务器请求表情图像的次数，由此可以进一步减少对网络资源的占用。
在本实施例的一些可选的实现方式中，获取用户输入至用户终端的用户输入信息，可以包括如下子步骤：获取用户输入至用户终端并且未发送至除该用户终端之外的其他用户终端的用户输入信息。
可以理解，用户在聊天软件中聊天的流程通常为：第一步，输入信息(即用户输入信息)至输入框。第二步，点击发送按键，以将输入的信息发送至该用户的聊天对象所使用的用户终端。在本可选的实现方式中，上述子步骤中的用户输入信息可以是在上述输入框中所呈现的信息，也即用户点击发送按键之前所输入的信息。由此，本可选的实现方式可以在用户将用户输入信息发送至该用户的聊天对象所指示的用户终端之前，为该用户终端推送表情图像，从而提高了图像推送的及时性。
继续参见图3A-图3C，图3A-图3C是根据本实施例的用于发送信息的方法的一个应用场景的示意图。在图3A的应用场景中，用户 向用户终端301输入了用户输入信息302(图示为类别为“微笑”的表情图像)。然后，服务器303从用户终端301获取到了用户输入信息302。接下来，请参考图3B，服务器303从目标表情图像集合304中，确定待发送至用户终端301并且与用户输入信息302相匹配的至少一个表情图像305，以及至少一个表情图像305的呈现顺序(例如随机呈现的呈现顺序)，之后，服务器303确定用户终端301在历史时间段内(例如30天)，按照上述呈现顺序对至少一个表情图像305进行呈现的次数小于等于目标次数(例如10)，因而，服务器303向用户终端301发送了呈现信息306。在这里，呈现信息306用于指示用户终端301按照随机呈现的呈现顺序呈现至少一个表情图像305。下面请参考图3C，用户终端301按随机呈现的呈现顺序呈现了至少一个表情图像305。
目前，在表情图像呈现场景中，现有技术之一是当用户输入用户输入信息(例如文字、表情等)时，按照用户使用表情图像的频率由高到低的顺序，来为用户呈现表情图像。在这种情况下，如果用户想要查找其未曾使用过，或者，使用频率较低的表情图像，则需要花费较多时间来查找，由此，一方面浪费了用户的时间，另一方面，还可能需要用户终端向服务器请求表情图像的次数，导致网络资源的占用较多。因此，针对上述问题，存在为用户推送与其输入的用户输入信息相匹配的，并且，使用频率较低的表情图像的需求。
本公开的上述实施例提供的方法，通过获取用户输入至用户终端的用户输入信息，然后，从目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，以及至少一个表情图像的呈现顺序，最后，在用户终端在历史时间段内，按照呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数的情况下，向用户终端发送呈现信息，以使用户终端按照呈现顺序呈现至少一个表情图像，由此降低了用户终端呈现表情图像的重复次数，有助于方便用户更快速查找到之前未发送过的表情，从而实现更快速的表情回复，此外，还可以减少用户查找表情图像的过程中，用户终端向服务器请求表情图像的次数，减少了对网络资源的占用。
进一步参考图4，其示出了用于发送信息的方法的又一个实施例的流程400。该用于发送信息的方法的流程400，包括以下步骤：
步骤401，获取用户输入至用户终端的表情图像。之后，执行步骤402。
在本实施例中，用于发送信息的方法的执行主体(例如图1所示的服务器)可以通过有线连接方式或者无线连接方式从用户终端(例如图1所示的终端设备101、102、103)，获取用户输入至该用户终端的表情图像。
其中，上述用户终端可以是上述用户所使用的终端，其可以与上述执行主体通信连接。
步骤402，将所获取到的表情图像输入至预先训练的深度神经网络，获得所获取的表情图像所属的类别。之后，执行步骤403。
在本实施例中，上述执行主体可以将步骤401所获取到的表情图像输入至预先训练的深度神经网络，获得所获取的表情图像所属的类别。其中，上述深度神经网络可以用于确定表情图像所属的类别。作为示例，上述深度神经网络可以是采用机器学习方法，对初始深度神经网络模型进行训练而得到的模型。
步骤403，获取目标表情图像集合。之后，执行步骤404。
在本实施例中，上述执行主体可以获取目标表情图像集合。其中，上述目标表情图像集合可以是大量的表情图像的集合。作为示例，目标表情图像集合可以是预定历史时间段(例如30天、7天等等)内，网络上所有的表情图像中，被用户发送的频率最高的预定数量(例如10000、100000)张表情图像的集合。
步骤404，确定距离目标表情图像集合的上次生成时间是否经过预设时长。之后，若是，则执行步骤405；若否，则执行步骤406。
在本实施例中，上述执行主体可以确定距离目标表情图像集合的上次生成时间是否经过预设时长。
步骤405，更新目标表情图像集合，生成新的目标表情图像集合。之后，执行步骤403。
在本实施例中，上述执行主体还可以更新目标表情图像集合，生成新的目标表情图像集合。
可以理解，在获取目标表情图像集合之后，可以每间隔预设时长，更新一次目标表情图像集合。
步骤406，从最近一次更新得到的目标表情图像集合中，查找属于所获得的类别的表情图像子集。之后，执行步骤407。
在本实施例中，上述执行主体可以从最近一次更新得到的目标表情图像集合中，查找属于所获得的类别的表情图像子集。
在这里，技术人员可以预先设置目标表情图像集合中的每个表情图像的类别，以便查找属于所获得的类别的表情图像子集。
步骤407，从表情图像子集中，选择待发送至用户终端的至少一个表情图像。之后，执行步骤408。
在本实施例中，上述执行主体可以从表情图像子集中，选择待发送至用户终端的至少一个表情图像。
在这里，上述执行主体可以采用多种方式，从表情图像子集中，选择待发送至用户终端的至少一个表情图像。
作为示例，上述执行主体可以从表情图像子集中，随机选择预定数量(例如9)个表情图像，作为待发送至用户终端的表情图像。
可选的，上述执行主体也可以从表情图像子集中，选择发送频率高于预设频率阈值的表情图像，作为待发送至用户终端的表情图像。
步骤408，确定至少一个表情图像的呈现顺序。之后，执行步骤409。
在本实施例中，上述执行主体可以确定至少一个表情图像的呈现顺序。其中，上述呈现顺序可以用于指示上述至少一个表情图像在用户终端进行呈现时的顺序。
在这里，上述执行主体可以采用多种方式，来确定上述至少一个表情图像的呈现顺序。
作为示例，上述执行主体可以随机确定上述至少一个表情图像的呈现顺序，从而随机呈现上述至少一个表情图像中的各个表情图像。
可选的，上述执行主体还可以首先确定上述至少一个表情图像中 的各个表情图像在该用户终端的呈现次数，从而将呈现次数升序或者降序的顺序，确定为上述至少一个表情图像的呈现顺序。
步骤409，响应于确定用户终端在历史时间段内，未按照上述呈现顺序对至少一个表情图像进行呈现，向用户终端发送呈现信息。
在本实施例中，上述执行主体可以在确定用户终端在历史时间段内，未按照上述呈现顺序对至少一个表情图像进行呈现的情况下，向用户终端发送呈现信息。其中，呈现信息用于指示用户终端按照上述所确定出的呈现顺序呈现至少一个表情图像。
需要说明的是，出上述所记载的内容之外，上述步骤401-步骤409还可以包括与图2对应的实施例，及其可选的实现方式相同的特征，产生相同的效果，本申请实施例在此不再赘述。
从图4中可以看出，与图2对应的实施例相比，本实施例中的用于发送信息的方法的流程400突出了采用深度神经网络来确定表情图像库(即上述目标表情图像集合)中与用户输入的表情图像相匹配的、待发送至用户终端的表情图像的步骤。由于现有技术中，通常采用生成式对抗网络(Generative Adversarial Networks，GAN)，来生成表情图像，其表情图像的生成多样性有限，而且容易产生模糊的图像。而本可选的实现方式中采用深度神经网络来对表情图像进行分类，从而从目标表情图像集合中，查找属于所获得的类别的表情图像子集，有助于直接从目标表情图像集合中查找出清晰的图像，进而将其发送至用户终端。
进一步参考图5，作为对上述各图所示方法的实现，本公开提供了一种用于发送信息的装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，除下面所记载的特征外，该装置实施例还可以包括与图2所示的方法实施例相同或相应的特征。该装置具体可以应用于各种电子设备中。
如图5所示，本实施例的用于发送信息的装置500包括：获取单元501、确定单元502和发送单元503。其中，获取单元501被配置成获取用户输入至用户终端的用户输入信息；确定单元502被配置成从 目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，以及至少一个表情图像的呈现顺序；发送单元503被配置成响应于确定用户终端在历史时间段内，按照呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数，向用户终端发送呈现信息，其中，呈现信息用于指示用户终端按照上述所确定出的呈现顺序呈现至少一个表情图像。
在本实施例中，用于发送信息的装置500的获取单元501可以通过有线连接方式或者无线连接方式从用户终端(例如图1所示的终端设备101、102、103)，获取用户输入至该用户终端的用户输入信息。
其中，上述用户终端可以是上述用户所使用的终端，其可以与上述执行主体通信连接。上述用户输入信息可以是用户向上述用户终端输入的各种信息。作为示例，该用户输入信息可以包括但不限于以下至少一项：文字信息、语音信息、图像信息(例如表情图像)等等。
在本实施例中，基于获取单元501得到的用户输入信息，上述确定单元502可以从目标表情图像集合中，确定待发送至用户终端并且与步骤201获取到的用户输入信息相匹配的至少一个表情图像，以及确定上述至少一个表情图像的呈现顺序。
其中，上述目标表情图像集合可以是大量的表情图像的集合。作为示例，目标表情图像集合可以是预定历史时间段(例如30天、7天等等)内，网络上所有的表情图像中，被用户发送的频率最高的预定数量(例如10000、100000)张表情图像的集合。与用户输入信息相匹配的表情图像，可以是包括用户输入信息的关键词的表情图像。上述呈现顺序可以用于指示上述至少一个表情图像在用户终端进行呈现时的顺序。
在本实施例中，在确定用户终端在历史时间段内，按照呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数的情况下，上述发送单元503可以向用户终端发送呈现信息。其中，呈现信息用于指示用户终端按照上述步骤202所确定出的呈现顺序呈现至少上述一个表情图像。其中，上述历史时间段可以是当前时间(例如开始执行该步骤203时)之前的时间段，也可以是当前时间之前的预定时间范 围内(例如以当前时间为终点的30天内)的时间段。
在本实施例的一些可选的实现方式中，用户输入信息为表情图像；以及确定单元502包括：第一确定子单元(图中未示出)被配置成从目标表情图像集合中，确定待发送至用户终端并且与所获取到的表情图像所属的类别相同的至少一个表情图像，作为与用户输入信息相匹配的至少一个表情图像。
在本实施例的一些可选的实现方式中，第一确定子单元包括：确定模块(图中未示出)被配置成从目标表情图像集合中，确定与所获取到的表情图像所属的类别相同的表情图像子集；选择模块(图中未示出)被配置成从表情图像子集中，选择待发送至用户终端的至少一个表情图像。
在本实施例的一些可选的实现方式中，确定模块包括：输入子模块(图中未示出)被配置成将所获取到的表情图像输入至预先训练的深度神经网络，获得所获取的表情图像所属的类别；查找子模块(图中未示出)被配置成从目标表情图像集合中，查找属于所获得的类别的表情图像子集。
在本实施例的一些可选的实现方式中，该装置500还包括：更新单元(图中未示出)被配置成响应于距离目标表情图像集合的上次生成时间经过预设时长，更新目标表情图像集合，生成新的目标表情图像集合。以及确定单元包括：第二确定子单元(图中未示出)被配置成从最近一次更新得到的目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像。
在本实施例的一些可选的实现方式中，目标次数为0。
在本实施例的一些可选的实现方式中，获取单元包括：获取子单元(图中未示出)被配置成获取用户输入至用户终端并且未发送至除用户终端之外的其他用户终端的用户输入信息。
本公开的上述实施例提供的装置，通过获取单元501获取用户输入至用户终端的用户输入信息，然后，确定单元502从目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，以及至少一个表情图像的呈现顺序，最后，发送单元503 响应于确定用户终端在历史时间段内，按照呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数，向用户终端发送呈现信息，其中，呈现信息用于指示用户终端按照上述所确定出的呈现顺序呈现至少一个表情图像，由此降低了用户终端待呈现的表情图像的重复次数，有助于方便用户更快速查找到之前未发送过的表情，从而实现更快速的表情回复，此外，还可以减少用户查找表情图像的过程中，用户终端向服务器请求表情图像的次数，减少了对网络资源的占用。
下面参考图6，其示出了适于用来实现本公开的实施例的服务器的计算机系统600的结构示意图。图6示出的服务器仅仅是一个示例，不应对本公开的实施例的功能和使用范围带来任何限制。
如图6所示，计算机系统600包括中央处理单元(CPU)601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储部分608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有系统600操作所需的各种程序和数据。CPU 601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
以下部件连接至I/O接口605：包括键盘、鼠标等的输入部分606；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分607；包括硬盘等的存储部分608；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分609。通信部分609经由诸如因特网的网络执行通信处理。驱动器610也根据需要连接至I/O接口605。可拆卸介质611，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器610上，以便于从其上读出的计算机程序根据需要被安装入存储部分608。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分609从网络上被下载和安装，和/或从 可拆卸介质611被安装。在该计算机程序被中央处理单元(CPU)601执行时，执行本公开的方法中限定的上述功能。
需要说明的是，本公开所述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，所述程序设计语言包括面向目标的程序设计语言—诸如Python、Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利 用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开的实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括获取单元、确定单元和生成单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，获取单元还可以被描述为“获取用户输入至用户终端的用户输入信息的单元”。
作为另一方面，本公开还提供了一种计算机可读介质，该计算机可读介质可以是上述实施例中描述的服务器中所包含的；也可以是单独存在，而未装配入该服务器中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该服务器执行时，使得该服务器：获取用户输入至用户终端的用户输入信息；从目标表情图像集合中，确定待发送至用户终端并且与用户输入信息相匹配的至少一个表情图像，以及至少一个表情图像的呈现顺序；响应于确定用户终端在历史时间段内，按照呈现顺序对至少一个表情图像进行呈现的次数小于等于目标次数，向用户终端发送呈现信息，其中，呈现信息用于指示用户终端按照上述所确定出的呈现顺序呈现至少一个表情图像。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说 明。本领域技术人员应当理解，本公开中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (16)

  1. 一种用于发送信息的方法，包括：
    获取输入至用户终端的用户输入信息；
    从目标表情图像集合中，确定待发送至所述用户终端并且与所述用户输入信息相匹配的至少一个表情图像，以及所述至少一个表情图像的呈现顺序；以及
    响应于确定所述用户终端在历史时间段内，按照所述呈现顺序对所述至少一个表情图像进行呈现的次数小于等于目标次数，向所述用户终端发送呈现信息，其中，所述呈现信息用于指示所述用户终端按照所述呈现顺序呈现所述至少一个表情图像。
  2. 根据权利要求1所述的方法，其中，所述用户输入信息为表情图像；以及
    所述从目标表情图像集合中，确定待发送至所述用户终端并且与所述用户输入信息相匹配的至少一个表情图像，包括：
    从目标表情图像集合中，确定待发送至所述用户终端并且与所获取到的表情图像所属的类别相同的至少一个表情图像，作为与所述用户输入信息相匹配的至少一个表情图像。
  3. 根据权利要求2所述的方法，其中，所述从目标表情图像集合中，确定待发送至所述用户终端并且与所获取到的表情图像所述的类别相同的至少一个表情图像，包括：
    从目标表情图像集合中，确定与所获取到的表情图像所属的类别相同的表情图像子集；以及
    从所述表情图像子集中，选择待发送至所述用户终端的至少一个表情图像。
  4. 根据权利要求3所述的方法，其中，所述从目标表情图像集合中，确定与所获取到的表情图像所属的类别相同的表情图像子集，包 括：
    将所获取到的表情图像输入至预先训练的深度神经网络，获得所获取的表情图像所属的类别；以及
    从目标表情图像集合中，查找属于所获得的类别的表情图像子集。
  5. 根据权利要求1-4任一所述的方法，其中，所述方法还包括：
    响应于距离目标表情图像集合的上次生成时间经过预设时长，更新目标表情图像集合，生成新的目标表情图像集合；以及
    所述从目标表情图像集合中，确定待发送至所述用户终端并且与所述用户输入信息相匹配的至少一个表情图像，包括：
    从最近一次更新得到的目标表情图像集合中，确定待发送至所述用户终端并且与所述用户输入信息相匹配的至少一个表情图像。
  6. 根据权利要求1-4任一所述的方法，其中，所述目标次数为0。
  7. 根据权利要求1-4任一所述的方法，其中，所述获取输入至用户终端的用户输入信息，包括：
    获取用户输入至用户终端并且未发送至除所述用户终端之外的其他用户终端的用户输入信息。
  8. 一种用于发送信息的装置，包括：
    获取单元，被配置成获取输入至用户终端的用户输入信息；
    确定单元，被配置成从目标表情图像集合中，确定待发送至所述用户终端并且与所述用户输入信息相匹配的至少一个表情图像，以及所述至少一个表情图像的呈现顺序；以及
    发送单元，被配置成响应于确定所述用户终端在历史时间段内，按照所述呈现顺序对所述至少一个表情图像进行呈现的次数小于等于目标次数，向所述用户终端发送呈现信息，其中，所述呈现信息用于指示所述用户终端按照所述呈现顺序呈现所述至少一个表情图像。
  9. 根据权利要求8所述的装置，其中，所述用户输入信息为表情图像；以及
    所述确定单元包括：
    第一确定子单元，被配置成从目标表情图像集合中，确定待发送至所述用户终端并且与所获取到的表情图像所属的类别相同的至少一个表情图像，作为与所述用户输入信息相匹配的至少一个表情图像。
  10. 根据权利要求9所述的装置，其中，所述第一确定子单元包括：
    确定模块，被配置成从目标表情图像集合中，确定与所获取到的表情图像所属的类别相同的表情图像子集；以及
    选择模块，被配置成从所述表情图像子集中，选择待发送至所述用户终端的至少一个表情图像。
  11. 根据权利要求10所述的装置，其中，所述确定模块包括：
    输入子模块，被配置成将所获取到的表情图像输入至预先训练的深度神经网络，获得所获取的表情图像所属的类别；以及
    查找子模块，被配置成从目标表情图像集合中，查找属于所获得的类别的表情图像子集。
  12. 根据权利要求8-11任一所述的装置，其中，所述装置还包括：
    更新单元，被配置成响应于距离目标表情图像集合的上次生成时间经过预设时长，更新目标表情图像集合，生成新的目标表情图像集合；以及
    所述确定单元包括：
    第二确定子单元，被配置成从最近一次更新得到的目标表情图像集合中，确定待发送至所述用户终端并且与所述用户输入信息相匹配的至少一个表情图像。
  13. 根据权利要求8-11任一所述的装置，其中，所述目标次数为 0。
  14. 根据权利要求8-11任一所述的装置，其中，所述获取单元包括：
    获取子单元，被配置成获取用户输入至用户终端并且未发送至除所述用户终端之外的其他用户终端的用户输入信息。
  15. 一种服务器，包括：
    一个或多个处理器；
    存储装置，其上存储有一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-7中任一所述的方法。
  16. 一种计算机可读介质，其上存储有计算机程序，其中，所述程序被处理器执行时实现如权利要求1-7中任一所述的方法。
PCT/CN2019/113903 2019-03-08 2019-10-29 用于发送信息的方法和装置 Ceased WO2020181783A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/118,588 US11706172B2 (en) 2019-03-08 2020-12-10 Method and device for sending information

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910175581.5A CN109873756B (zh) 2019-03-08 2019-03-08 用于发送信息的方法和装置
CN201910175581.5 2019-03-08

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/118,588 Continuation US11706172B2 (en) 2019-03-08 2020-12-10 Method and device for sending information

Publications (1)

Publication Number Publication Date
WO2020181783A1 true WO2020181783A1 (zh) 2020-09-17

Family

ID=66920057

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/113903 Ceased WO2020181783A1 (zh) 2019-03-08 2019-10-29 用于发送信息的方法和装置

Country Status (3)

Country Link
US (1) US11706172B2 (zh)
CN (1) CN109873756B (zh)
WO (1) WO2020181783A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109873756B (zh) * 2019-03-08 2020-04-03 百度在线网络技术（北京）有限公司 用于发送信息的方法和装置
CN112532507B (zh) * 2019-09-17 2023-05-05 上海掌门科技有限公司 用于呈现表情图像、用于发送表情图像的方法和设备
CN112462992B (zh) * 2020-11-30 2022-07-19 北京搜狗科技发展有限公司 一种信息处理方法、装置、电子设备及介质
CN112650399B (zh) * 2020-12-22 2023-12-01 科大讯飞股份有限公司 表情推荐方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130283303A1 (en) * 2012-04-23 2013-10-24 Electronics And Telecommunications Research Institute Apparatus and method for recommending content based on user's emotion
CN104298429A (zh) * 2014-09-25 2015-01-21 北京搜狗科技发展有限公司 一种基于输入的信息展示方法和输入法系统
CN104866116A (zh) * 2015-03-25 2015-08-26 百度在线网络技术（北京）有限公司 一种用于输出表情信息的方法和装置
CN105630849A (zh) * 2014-11-27 2016-06-01 英业达科技有限公司 表情图像推荐系统及其方法
CN108038102A (zh) * 2017-12-08 2018-05-15 北京小米移动软件有限公司 表情图像的推荐方法、装置、终端及存储介质
CN109873756A (zh) * 2019-03-08 2019-06-11 百度在线网络技术（北京）有限公司 用于发送信息的方法和装置

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140164507A1 (en) * 2012-12-10 2014-06-12 Rawllin International Inc. Media content portions recommended
CN104076944B (zh) * 2014-06-06 2017-03-01 北京搜狗科技发展有限公司 一种聊天表情输入的方法和装置
CN104063427A (zh) * 2014-06-06 2014-09-24 北京搜狗科技发展有限公司 一种基于语义理解的表情输入方法和装置
JP2016090775A (ja) * 2014-11-04 2016-05-23 トヨタ自動車株式会社 応答生成装置、応答生成方法およびプログラム
US10025972B2 (en) * 2015-11-16 2018-07-17 Facebook, Inc. Systems and methods for dynamically generating emojis based on image analysis of facial features
CN105871695B (zh) * 2016-05-19 2019-03-26 腾讯科技（深圳）有限公司 表情发送方法和装置
CN106021599A (zh) * 2016-06-08 2016-10-12 维沃移动通信有限公司 一种表情符号推荐方法及移动终端
CN106293738B (zh) * 2016-08-09 2020-03-17 腾讯科技（深圳）有限公司 一种表情图像的更新方法及装置
CN107797717B (zh) * 2016-09-02 2021-08-20 阿里巴巴集团控股有限公司 推送方法、显示方法、客户端设备和数据处理系统
CN109154979A (zh) * 2016-10-26 2019-01-04 奥康科技有限公司 用于分析图像和提供反馈的可佩戴设备和方法
US20180275747A1 (en) * 2017-03-25 2018-09-27 Camille Suzanne Campbell Portable emoji display and control
DK180007B1 (en) * 2017-05-16 2020-01-16 Apple Inc. RECORDING AND SENDING EMOJI
DK179948B1 (en) * 2017-05-16 2019-10-22 Apple Inc. Recording and sending Emoji
US10397350B2 (en) * 2017-09-26 2019-08-27 Disney Enterprises, Inc. Tracking wearables or other devices for emoji stories
US10706271B2 (en) * 2018-04-04 2020-07-07 Thomas Floyd BRYANT, III Photographic emoji communications systems and methods of use
CN111258435B (zh) * 2020-01-15 2024-05-07 北京达佳互联信息技术有限公司 多媒体资源的评论方法、装置、电子设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130283303A1 (en) * 2012-04-23 2013-10-24 Electronics And Telecommunications Research Institute Apparatus and method for recommending content based on user's emotion
CN104298429A (zh) * 2014-09-25 2015-01-21 北京搜狗科技发展有限公司 一种基于输入的信息展示方法和输入法系统
CN105630849A (zh) * 2014-11-27 2016-06-01 英业达科技有限公司 表情图像推荐系统及其方法
CN104866116A (zh) * 2015-03-25 2015-08-26 百度在线网络技术（北京）有限公司 一种用于输出表情信息的方法和装置
CN108038102A (zh) * 2017-12-08 2018-05-15 北京小米移动软件有限公司 表情图像的推荐方法、装置、终端及存储介质
CN109873756A (zh) * 2019-03-08 2019-06-11 百度在线网络技术（北京）有限公司 用于发送信息的方法和装置

Also Published As

Publication number Publication date
CN109873756A (zh) 2019-06-11
US11706172B2 (en) 2023-07-18
CN109873756B (zh) 2020-04-03
US20210097262A1 (en) 2021-04-01

Similar Documents

Publication Publication Date Title
US11487503B2 (en) Interactive control method and device for voice and video communications
CN108022586B (zh) 用于控制页面的方法和装置
JP6718828B2 (ja) 情報入力方法および装置
CN109190114B (zh) 用于生成回复信息的方法和装置
CN110309275B (zh) 一种对话生成的方法和装置
US11706172B2 (en) Method and device for sending information
CN110059172B (zh) 基于自然语言理解的推荐答案的方法和装置
CN111428010A (zh) 人机智能问答的方法和装置
CN112532507B (zh) 用于呈现表情图像、用于发送表情图像的方法和设备
CN112929253A (zh) 一种虚拟形象交互方法和装置
CN109582825B (zh) 用于生成信息的方法和装置
CN114446305A (zh) 使用观众反馈的个人语音推荐
CN107452378A (zh) 基于人工智能的语音交互方法和装置
CN116450920A (zh) 数据查询方法、装置及电子设备
CN116204624A (zh) 应答方法、装置、电子设备及存储介质
CN116628313A (zh) 内容推荐方法及装置、电子设备和存储介质
CN113068077B (zh) 一种字幕文件处理方法及装置
US20250258723A1 (en) Generating synthetic data for training llms with tool use capabilities
CN114036397B (zh) 数据推荐方法、装置、电子设备和介质
CN107968743B (zh) 推送信息的方法和装置
CN118764681A (zh) 针对视频的交互方法和针对视频的处理方法、装置
CN110288683B (zh) 用于生成信息的方法和装置
CN112308016B (zh) 表情图像获取方法、装置、电子设备及存储介质
CN107526827A (zh) 用于问答展示的方法、设备和计算机可读存储介质
CN110442806A (zh) 用于识别图像的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19919040

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 01/02/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19919040

Country of ref document: EP

Kind code of ref document: A1