WO2021068493A1 - 用于处理信息的方法和装置 - Google Patents

用于处理信息的方法和装置 Download PDF

Info

Publication number
WO2021068493A1
WO2021068493A1 PCT/CN2020/088369 CN2020088369W WO2021068493A1 WO 2021068493 A1 WO2021068493 A1 WO 2021068493A1 CN 2020088369 W CN2020088369 W CN 2020088369W WO 2021068493 A1 WO2021068493 A1 WO 2021068493A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
preset
dialogue
user
dialogue information
Prior art date
Application number
PCT/CN2020/088369
Other languages
English (en)
French (fr)
Inventor
王慧
肖楠
Original Assignee
京东数字科技控股有限公司
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 京东数字科技控股有限公司 filed Critical 京东数字科技控股有限公司
Priority to US17/767,262 priority Critical patent/US20220391425A1/en
Priority to EP20874910.1A priority patent/EP4044044A4/en
Publication of WO2021068493A1 publication Critical patent/WO2021068493A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G06F16/355—Class or cluster creation or modification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology

Definitions

  • the embodiments of the present disclosure relate to the field of computer technology, and in particular to methods and devices for processing information.
  • Human-machine dialogue is a sub-direction of the field of artificial intelligence. In layman's terms, people can interact with machines through human language (i.e. natural language). As one of the problems of artificial intelligence, a complete human-machine dialogue system involves a wide range of technologies, such as speech processing technology, natural language processing technology, and machine learning technology.
  • the embodiments of the present disclosure propose methods and devices for processing information.
  • the embodiments of the present disclosure provide a method for processing information, the method includes: in response to receiving dialog information input by the user, determining whether the user corresponds to historical reply information, wherein the historical reply information is a response to the user In response to determining the historical reply information corresponding to the user, based on the received dialogue information and the historical reply information corresponding to the user, determine whether the preset dialogue information set includes the target dialogue information corresponding to the user, wherein the preset The dialogue information corresponds to the preset reply information and the preset history reply information.
  • the preset reply information is used to reply to the corresponding preset dialogue information
  • the preset history reply information is used to reply to the historical dialogue information relative to the corresponding preset dialogue information.
  • the dialogue information is preset dialogue information that matches the received dialogue information and the corresponding preset historical reply information matches the user’s corresponding historical reply information; in response to the preset dialogue information set including the target dialogue information, the included The preset reply message corresponding to the target dialogue message is sent to the user.
  • determining whether the preset dialogue information set includes the target dialogue information corresponding to the user includes: determining whether the preset dialogue information set includes the The candidate dialogue information that matches the dialogue information; in response to the inclusion, it is determined whether the included candidate dialogue information includes target dialogue information whose corresponding preset historical reply information matches the user's corresponding historical reply information.
  • the preset dialog information set includes preset numerical range dialog information, the preset numerical range dialog information is used to indicate the numerical range, and the preset historical reply information corresponding to the preset numerical range dialog information corresponds to at least two preset values.
  • a numerical range, the numerical range indicated by the dialog information of the preset numerical range belongs to at least two numerical ranges corresponding to the corresponding preset historical reply information; and based on the received dialog information and the historical reply information corresponding to the user, the preset is determined Whether the dialog information set includes the target dialog information corresponding to the user includes: determining whether the received dialog information indicates a value; in response to the received dialog information indicating a value, determining whether the historical reply information corresponding to the user corresponds to at least two preset values Range; in response to at least two preset numerical ranges corresponding to the historical reply information, determine the numerical range to which the value indicated by the received dialogue information belongs from the at least two numerical ranges corresponding to the historical reply information corresponding to the user as the target Numerical value range; determine whether the
  • the method further includes: in response to the preset dialogue information set does not include the target dialogue information corresponding to the user, sending the preset general reply information to the user.
  • sending preset reply information corresponding to the included target dialogue information to the user includes: responding to the preset dialogue information set including at least two The target dialogue information corresponding to each user sends the preset reply information corresponding to the target dialogue information that most closely matches the received dialogue information among the included at least two target dialogue information to the user.
  • the method further includes: in response to determining that the user does not correspond to the historical reply information, determining whether the preset dialogue information set includes candidate dialogue information matching the received dialogue information; in response to the preset dialogue information set The candidate dialogue information corresponding to the user is included, and the preset reply information corresponding to the included candidate dialogue information is sent to the user.
  • the historical reply information is a reply to the previous round of historical dialogue information relative to the current round of dialogue information.
  • an embodiment of the present disclosure provides an apparatus for processing information.
  • the apparatus includes: a first determining unit configured to determine whether the user corresponds to the historical reply information in response to receiving the dialog information input by the user, Wherein, the historical reply information is a historical reply to the user's historical dialogue information; the second determining unit is configured to determine the preset based on the received dialogue information and the historical reply information corresponding to the user in response to determining the historical reply information corresponding to the user Does the dialogue information set include the target dialogue information corresponding to the user, where the preset dialogue information corresponds to the preset reply information and the preset history reply information, the preset reply information is used to reply to the corresponding preset dialogue information, and the preset history reply information is used Regarding the historical dialogue information that responds to the corresponding preset dialogue information, the target dialogue information is the preset dialogue information that matches the received dialogue information and the corresponding preset historical reply information matches the user's corresponding historical reply information
  • the first sending unit is configured to, in response to the preset dialog information set including target
  • embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device, on which one or more programs are stored, when one or more programs are processed by one or more The processor executes, so that one or more processors implement the method of any one of the foregoing methods for processing information.
  • the embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the method of any one of the above methods for processing information is implemented.
  • the method and apparatus for processing information determine whether the user corresponds to the historical reply information by responding to the dialogue information input by the user, wherein the historical reply information is a historical reply to the historical dialogue information of the user , And then in response to determining the user's corresponding historical reply information, based on the received dialogue information and the user's corresponding historical reply information, it is determined whether the preset dialogue information set includes the target dialogue information corresponding to the user, wherein the preset dialogue information corresponds to the preset reply Information and preset historical reply information, the preset reply information is used to reply to the corresponding preset dialogue information, the preset historical reply information is used to reply to the historical dialogue information relative to the corresponding preset dialogue information, and the target dialogue information is with the received The preset dialogue information that matches the dialogue information and the corresponding preset historical reply information matches the user’s corresponding historical reply information.
  • the included target dialogue information is The corresponding preset reply information is sent to the user, so that when replying to the dialogue information currently input by the user, the historical reply information sent to the user in the historical dialogue process can be used as a reference factor, and further, the dialogue information currently input by the user can be comprehensively considered.
  • the background of the user inputting the dialogue information can be used to answer the user more accurately and effectively, which helps to improve the accuracy and effectiveness of the man-machine dialogue.
  • Fig. 1 is an exemplary system architecture diagram to which an embodiment of the present disclosure can be applied;
  • Fig. 2 is a flowchart of an embodiment of a method for processing information according to the present disclosure
  • Fig. 3 is a schematic diagram of an application scenario of the method for processing information according to an embodiment of the present disclosure
  • Fig. 4 is a flowchart of another embodiment of a method for processing information according to the present disclosure.
  • Fig. 5 is a schematic structural diagram of an embodiment of an apparatus for processing information according to the present disclosure
  • Fig. 6 is a schematic structural diagram of a computer system suitable for implementing an electronic device of an embodiment of the present disclosure.
  • FIG. 1 shows an exemplary system architecture 100 to which an embodiment of the method for processing information or the apparatus for processing information 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, and so on.
  • the user can use the terminal devices 101, 102, and 103 to interact with the server 105 through the network 104 to receive or send messages and so on.
  • Various communication client applications such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, and social platform software, may be installed on the terminal devices 101, 102, and 103.
  • the terminal devices 101, 102, 103 may be hardware or software.
  • the terminal devices 101, 102, 103 can be various electronic devices with information processing functions, including but not limited to smart phones, tablet computers, e-book readers, 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, multiple software or software modules for providing 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, an information processing server that processes dialog information sent by the terminal devices 101, 102, and 103.
  • the dialog information sent by the terminal devices 101, 102, 103 may be the dialog information input by the user on the terminal devices 101, 102, 103.
  • the information processing server can analyze and process the received dialogue information and other data to obtain the processing result (for example, the preset reply information corresponding to the target dialogue information), and the information processing server can also feed back the processing result to the terminal device for the terminal The device feeds back the processing result to the user.
  • the method for processing information provided by the embodiments of the present disclosure can be executed by the terminal device 101, 102, 103, or by the server 105. Accordingly, the device for processing information can be set in the terminal. The devices 101, 102, and 103 may also be 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, multiple software or software modules for providing distributed services), or as a single software or software module. There is no specific limitation here.
  • 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 method for processing information includes the following steps:
  • Step 201 In response to receiving the dialog information input by the user, it is determined whether the user corresponds to the historical reply information.
  • the execution body of the method for processing information may respond to the remote or local reception of the dialog information input by the user through a wired connection or a wireless connection, Determine whether the user corresponds to the historical reply information.
  • the historical reply information is a historical reply to the historical dialogue information of the user.
  • the historical dialogue information is dialogue information input by the user before receiving the dialogue information currently input by the user.
  • the historical reply information may be used to reply to the last round of historical dialogue information relative to the current round of dialogue information.
  • the dialogue information of this round is the dialogue information currently received.
  • the historical reply information is the most recently output information used to reply to the user. It can be understood that in the dialogue process, the dialogue information and reply information that are adjacent to each other are usually related. Therefore, this implementation method uses the last historical reply information output to the user as a reference for replying to the dialogue information currently input by the user, which is helpful Determine the prerequisite background for the current user to input the dialogue information, and then help to answer the user more effectively.
  • the historical reply information corresponding to the user may be "recommend restaurant A and restaurant B for you", and the dialogue information currently received may be "what special dishes does restaurant A have”.
  • the above-mentioned dialogue information may be various information input by the user for dialogue with the machine, including but not limited to at least one of the following: text information, Voice information, image information, and video information.
  • the reply information may be various information used to reply to the dialogue information, including but not limited to at least one of the following: text information, voice information, image information, and video information.
  • the dialogue information may be the voice "what delicious restaurants are around", and the corresponding reply information may be the voice "recommend restaurant A and restaurant B for you".
  • the execution subject may record the dialogue with the user, and further, the execution subject may determine whether the user corresponds to the historical reply information through the dialogue record.
  • the above-mentioned execution subject may use the user's user tag (for example, user ID) as a key, and the most recent response information output to the user as a value (value), and mark the user with the user in the form of a key-value pair.
  • the corresponding most recent reply information is stored in the database.
  • the above-mentioned execution subject may also replace the reply information corresponding to the user stored in the database with the latest reply information each time a new conversation is generated with the user.
  • the execution subject may determine whether the user corresponds to the historical reply information by determining whether the user mark of the user is included in the database.
  • Step 202 In response to determining the historical reply information corresponding to the user, based on the received dialogue information and the historical reply information corresponding to the user, determine whether the preset dialogue information set includes target dialogue information corresponding to the user.
  • the above-mentioned executive body may determine whether the preset dialogue information set includes the target dialogue information corresponding to the user based on the received dialogue information and the historical reply information corresponding to the user.
  • the preset dialogue information corresponds to the preset reply information and the preset history reply information
  • the preset reply information is used to reply to the corresponding preset dialogue information
  • the preset history reply information is used to reply to the history relative to the corresponding preset dialogue information.
  • Dialogue information That is, the preset historical reply information is the information generated before the corresponding preset dialog information and used to reply to the dialog information.
  • the preset dialogue information may be "How much is the ticket for scenic spot C”
  • the preset historical reply information corresponding to the preset dialogue information may be "Recommend scenic spots C and D for you", which corresponds to the preset dialogue information
  • the preset reply information can be "60 yuan/person”.
  • the preset historical reply message "Recommend C and D attractions for you” can be used to reply to the dialogue message "What are some good spots in City M”. It is not difficult to understand that the dialogue message "What are some good spots in City M?" "Is the dialogue information generated before the preset dialogue information "How much is the ticket for scenic spot C", that is, historical dialogue information relative to the preset dialogue information "How much is the ticket for scenic spot C”.
  • the preset dialogue information and the preset reply information and the preset historical reply information corresponding to the preset dialogue information are predetermined corpus used for dialogue with the user.
  • the above-mentioned executive body can collect the generated dialogue information and reply information while conducting a dialogue with the user based on the corpus, and use the collected dialogue information and reply information as the corpus for the follow-up dialogue, which can be used to communicate with the user.
  • the corpus of the user's dialogue is richer, which helps to increase the diversity of man-machine dialogue.
  • the target dialogue information is preset dialogue information that matches the received dialogue information and the corresponding preset historical reply information matches the historical reply information corresponding to the user.
  • matching can mean similar or identical.
  • two pieces of information whose similarity is greater than or equal to a preset threshold can be called similar information (that is, matched information).
  • the preset threshold may be a value predetermined by a technician.
  • the preset threshold may be 0.85 (the similarity degree ranges from 0 to 1).
  • the above-mentioned execution subject may adopt various methods to determine whether the preset dialogue information set includes the target dialogue information corresponding to the user.
  • the above-mentioned execution subject may first determine whether the preset dialogue information set includes candidate dialogue information that matches the received dialogue information.
  • the candidate dialogue information is the preset dialogue information matching the received dialogue information.
  • the above-mentioned executive body may determine whether the included candidate dialog information includes the corresponding preset historical reply information corresponding to the user The historical reply information matches the target dialogue information.
  • the target dialogue information can be determined by a stepwise screening method, that is, the candidate dialogue information is first determined based on the matching of the dialogue information, and then based on the matching of the historical reply information, the target dialogue information is determined from the candidate dialogue information, as opposed to directly from the preset In the dialog information collection, search for preset dialog information that meets both the dialog information matching and historical response information matching conditions.
  • This implementation can reduce the workload of determining the target dialog information and help reduce the consumption in the process of responding to users Resources to improve the efficiency of responding to users.
  • the above-mentioned executive body may also determine whether the preset dialogue information set includes candidate dialogue information matching the received dialogue information in response to determining that the user does not correspond to the historical reply information, And in response to the preset dialogue information set including candidate dialogue information corresponding to the user, the preset reply information corresponding to the included candidate dialogue information is sent to the user.
  • Step 203 In response to the preset dialogue information set including the target dialogue information, the preset reply information corresponding to the included target dialogue information is sent to the user.
  • the above-mentioned execution subject may respond to the preset dialogue information set including the target dialogue information corresponding to the user, and send the preset reply information corresponding to the included target dialogue information to the user.
  • the execution subject can directly output the preset reply information corresponding to the target dialogue information; if the execution subject interacts with the user through the user terminal, the execution subject can transfer the target dialogue information The corresponding preset reply information is sent to the user terminal used by the user, so that the user terminal can output the received preset reply information to the user.
  • the above-mentioned execution subject may also send the preset general reply information to the user in response to the preset dialogue information set not including the target dialogue information corresponding to the user.
  • the preset general reply information is preset and used to respond to the user when the preset reply information for replying to the user cannot be found from the preset corpus.
  • the preset general reply message can be "Excuse me, I haven't learned how to answer this question, you can transfer to manual service".
  • the above-mentioned executive body may also respond to the preset dialog information set including at least two user-corresponding target dialog information, and compare the included at least two target dialog information with the received target dialog information.
  • the preset reply message corresponding to the target dialogue message that best matches the dialogue information of the user is sent to the user.
  • the most matching target dialogue information may be the target dialogue information with the highest similarity to the received dialogue information; it may also be the target dialogue information with the highest similarity between the corresponding preset historical reply information and the historical reply information corresponding to the user.
  • FIG. 3 is a schematic diagram of an application scenario of the method for processing information according to this embodiment.
  • the mobile phone 301 can determine whether the user 302 corresponds to the historical reply information in response to receiving the dialogue information 303 input by the user 302 (for example, "What is the characteristic of restaurant A?"). It is a historical reply to the historical dialogue information of the user 302.
  • the mobile phone 301 can respond to determining that the user 302 corresponds to the historical reply information 304 (for example, "Here recommends delicious restaurants A and B for you", as an example, "recommends delicious restaurants A and B for you here" can be the right answer.
  • the historical reply information 304 for example, "Here recommends delicious restaurants A and B for you", as an example, "recommends delicious restaurants A and B for you here" can be the right answer.
  • the user s historical dialogue information "please help recommend a restaurant in City A"
  • the preset dialogue information set 305 includes the target corresponding to the user 302 Dialogue information
  • the preset dialogue information corresponds to the preset reply information and the preset history reply information
  • the preset reply information is used to reply to the corresponding preset dialogue information
  • the preset history reply information is used to reply to the corresponding preset dialogue
  • the historical dialogue information of the message, the target dialogue information is the preset dialogue information that matches the received dialogue information 303 and the corresponding preset historical reply information matches the historical reply information 304 corresponding to the user 302.
  • the mobile phone 301 can respond to the preset dialogue information set 305 including the target dialogue information 306 corresponding to the user 302 (for example, "What is the specialty of restaurant A?”), and then send the preset reply information corresponding to the included target dialogue information 306 307 (for example, "pot-in-pot meat") is sent to the user 302.
  • the preset reply information corresponding to the included target dialogue information 306 307 for example, "pot-in-pot meat
  • the method provided by the above-mentioned embodiments of the present disclosure can use the historical reply information sent to the user during the historical dialogue as a reference factor when replying to the dialogue information currently input by the user, and further, can comprehensively consider the dialogue information currently input by the user and the user input
  • the background of the dialogue information in this way, can answer the user more accurately and effectively, which helps to improve the accuracy and effectiveness of the man-machine dialogue.
  • FIG. 4 shows a flow 400 of yet another embodiment of a method for processing information.
  • the process 400 of the method for processing information includes the following steps:
  • Step 401 In response to receiving the dialogue information input by the user, it is determined whether the user corresponds to the historical reply information.
  • the execution body of the method for processing information may respond to the remote or local reception of the dialog information input by the user through a wired connection or a wireless connection, Determine whether the user corresponds to the historical reply information.
  • the historical reply information is a historical reply to the historical dialogue information of the user.
  • the historical dialogue information is dialogue information input by the user before receiving the dialogue information currently input by the user.
  • Step 402 in response to determining that the user corresponds to the historical reply information, determine whether the received dialog information indicates a value.
  • the above-mentioned execution subject may determine whether the dialogue information received in step 401 indicates a numerical value in response to determining that the user corresponds to the historical reply information.
  • the received dialogue information may be "170cm in height", the dialogue information may indicate the value 170; or, the received dialogue information may be "I am 21 years old", the dialogue information may indicate the value "21" .
  • Step 403 In response to the received dialogue information indicating the value, it is determined whether the historical reply information corresponding to the user corresponds to at least two preset value ranges.
  • the above-mentioned executive body may determine whether the historical reply information corresponding to the user corresponds to at least two preset numerical ranges in response to the received dialogue information indicating the numerical value.
  • the reply information used to reply to the user is preset information, and for the reply information used to obtain the characteristic values of the specific characteristics input by the user (such as height characteristics, age characteristics, etc.), the technician can also target At least two numerical ranges are preset for the reply message, so that after the user inputs different characteristic values, different reply messages can be selected for reply according to the numerical range to which the characteristic values belong. It should be noted that the at least two numerical ranges preset for the reply information may be at least two mutually exclusive numerical ranges.
  • the historical reply information can be "What is your height?"
  • three numerical ranges that is, at least two numerical ranges
  • the user enters the dialogue information "My Height 165” he can select [160,170] the corresponding reply message "It is recommended that you choose M code” and output to the user; when the user enters the dialogue information "My Height 155", You can select [150,160] the corresponding reply message “Suggest you choose the S code” to output to the user; when the user enters the dialogue message "My height is 175", you can choose [170,180] the corresponding reply message "Suggest you choose the L code” to output to the user user.
  • Step 404 In response to at least two preset numerical ranges corresponding to the historical reply information, determine from the at least two numerical ranges corresponding to the historical reply information corresponding to the user the numerical range to which the numerical value indicated by the received dialogue information belongs as Target value range.
  • the above-mentioned executive body may, in response to at least two preset numerical ranges corresponding to the historical reply information, determine from the at least two numerical ranges corresponding to the historical reply information corresponding to the user what is indicated by the received dialogue information
  • the numerical range to which the numerical value belongs is regarded as the target numerical range.
  • the dialog information entered by the user can be "My height is 155”
  • the historical reply message "What is your height” can correspond to three numerical ranges, namely "[150,160]; [160,170]; [170,180]” , Since the value 155 indicated by the dialogue message "My Height 155" belongs to the value range [150,160], the value range [150,160] can be determined as the target value range.
  • the reply information and at least two numerical ranges corresponding to the reply information are usually stored in association.
  • the numerical range can be stored in various forms, for example, it can be stored in the form of graphics, or in the form of Boolean expressions. It can be understood that when the value range is stored in the form of a Boolean expression, the target value range is the value range corresponding to the true Boolean expression after the value indicated by the dialog information is substituted into the Boolean expression.
  • Step 405 Determine whether the dialog information of the preset value range included in the preset dialog information set includes candidate dialog information whose indicated value range matches the target value range.
  • the preset dialogue information set includes preset numerical range dialogue information
  • the preset numerical range dialogue information is used to indicate the numerical range
  • the preset historical reply information corresponding to the preset numerical range dialogue information corresponds to at least two preset values.
  • a numerical range, the numerical range indicated by the dialog information of the preset numerical range belongs to at least two numerical ranges corresponding to the corresponding preset historical reply information, and then based on the target numerical range obtained in step 404, the above-mentioned executive body can determine the preset Whether the dialogue information of the preset numerical range included in the dialogue information set includes candidate dialogue information whose indicated numerical range matches the target numerical range.
  • matching can refer to the same or similar.
  • the preset value range dialog information may be various information used to indicate the value range, including but not limited to at least one of the following: text, numbers, symbols, images, audio, and video.
  • Step 406 in response to the inclusion, determine whether the included candidate dialog information includes target dialog information whose corresponding preset historical reply information matches the historical reply information corresponding to the user.
  • the above-mentioned executive body may determine the included candidate dialogue information in response to determining that the preset numerical range dialogue information included in the preset dialogue information set includes the indicated numerical range matching the target numerical range. Whether the information includes target dialogue information in which the corresponding preset historical reply information matches the corresponding historical reply information of the user.
  • the target value range is [150,160]
  • the preset dialogue information can include the preset value range dialogue information "Between 150cm and 160cm” and the preset value range dialogue information "Weight is between 150 kg and 160 kg.
  • the two preset value range dialog messages indicate the value range [150,160], which is the same as the target value range (that is, match), and the above-mentioned executive body can combine the two preset value range dialog messages Determined as candidate dialogue information.
  • the historical reply information corresponding to the user can be "What is your height", and the preset historical reply information corresponding to the determined candidate dialogue information "The height is between 150cm and 160cm” can be “Excuse me, your height” How much is it”; the preset historical reply message corresponding to the candidate dialogue information "Weight is between 150 kg and 160 kg” can be "How much is your weight”, because the candidate dialogue information "Height is between 150cm and 160cm”
  • the corresponding preset historical reply information is the same as the historical reply information corresponding to the user (that is, it matches), so the above-mentioned executive body can determine that the candidate dialogue information includes the corresponding preset historical reply information and the historical reply information corresponding to the user
  • the matching target dialogue message that is, "the height is between 150cm and 160cm”.
  • the user's dialogue information indicates a value
  • the preset dialogue information set it is difficult to enumerate all the possible values entered by the user; on the other hand, even if the two dialogue messages indicating the numerical value are similar in form, as long as the two If the values indicated by the two dialog messages are different, the actual meanings of the two dialog messages may be quite different. For example, for the dialogue message "I am 8 years old this year" and the dialogue message "I am 80 years old", although the two dialogue messages are similar, their actual meanings are far from each other.
  • this embodiment adopts a method of characterizing the numerical value indicated by the received dialogue information as the target numerical range, and then determining the target dialogue information based on the matching of the numerical range, so as to improve the dialogue related to the numerical value input by the user. Information on the validity of the reply.
  • Step 407 In response to the target dialogue information being included in the candidate dialogue information, the preset reply information corresponding to the included target dialogue information is sent to the user.
  • the above-mentioned execution subject may compare the included target dialogue information corresponding to the target dialogue information. Let the reply message be sent to the user.
  • step 401 and step 407 can be respectively performed in a manner similar to step 201 and step 203 in the foregoing embodiment.
  • step 201 and step 203 also applies to step 401 and step 407, and will not be repeated here.
  • the flow 400 of the method for processing information in this embodiment highlights that in the case where the dialog information input by the user indicates a value, based on the dialog information
  • the solution described in this embodiment can realize a reply to the dialogue information input by the user and related to the numerical value, which improves the applicability and diversity of the man-machine dialogue.
  • the present disclosure provides an embodiment of a device for processing information.
  • the device embodiment corresponds to the method embodiment shown in FIG.
  • the device can be specifically applied to various electronic devices.
  • the apparatus 500 for processing information in this embodiment includes: a first determining unit 501, a second determining unit 502, and a first sending unit 503.
  • the first determining unit 501 is configured to determine whether the user corresponds to historical reply information in response to receiving the dialogue information input by the user, wherein the historical reply information is a historical reply to the user’s historical dialogue information
  • the second determining unit 502 is configured to It is configured to determine whether the preset dialogue information set includes target dialogue information corresponding to the user based on the received dialogue information and the historical reply information corresponding to the user in response to determining the historical reply information corresponding to the user, wherein the preset dialogue information corresponds to the preset reply Information and preset historical reply information, the preset reply information is used to reply to the corresponding preset dialogue information, the preset historical reply information is used to reply to the historical dialogue information relative to the corresponding preset dialogue information, and the target dialogue information is with the received
  • the first sending unit 503 is configured to respond to the preset dialogue information set including the target dialogue
  • the first determining unit 501 of the apparatus 500 for processing information may determine whether the user corresponds to the historical reply information in response to receiving the dialogue information input by the user remotely or locally through a wired connection or a wireless connection.
  • the historical reply information is a historical reply to the historical dialogue information of the user.
  • the historical dialogue information is dialogue information input by the user before receiving the dialogue information currently input by the user.
  • the second determining unit 502 may, in response to determining the historical reply information corresponding to the user, determine whether the preset dialogue information set includes the target dialogue information corresponding to the user based on the received dialogue information and the historical reply information corresponding to the user.
  • the preset dialogue information corresponds to the preset reply information and the preset history reply information
  • the preset reply information is used to reply to the corresponding preset dialogue information
  • the preset history reply information is used to reply to the history relative to the corresponding preset dialogue information.
  • Dialogue information That is, the preset historical reply information is the information generated before the corresponding preset dialog information and used to reply to the dialog information.
  • the target dialogue information is preset dialogue information that matches the received dialogue information and the corresponding preset historical reply information matches the historical reply information corresponding to the user.
  • matching can mean similar or identical.
  • the first sending unit 503 may respond to the preset dialogue information set including the target dialogue information corresponding to the user, and send the preset reply information corresponding to the included target dialogue information to the user.
  • the second determining unit 502 may include: a first determining module (not shown in the figure) configured to determine whether the preset dialog information set includes the received dialog Candidate dialogue information that matches the information; the second determining module (not shown in the figure) is configured to, in response to the inclusion, determine whether the included candidate dialogue information includes the corresponding preset history reply information and the history corresponding to the user The reply message matches the target conversation message.
  • the preset dialog information set includes dialog information of a preset value range
  • the preset value range dialog information is used to indicate a value range
  • the preset history response corresponding to the preset value range dialog information The information corresponds to at least two preset value ranges, and the value range indicated by the preset value range dialog information belongs to at least two value ranges corresponding to the corresponding preset historical reply information; and the second determining unit 502 may include: third The determining module (not shown in the figure) is configured to determine whether the received dialog information indicates a value; the fourth determining module (not shown in the figure) is configured to determine the user in response to the received dialog information indicating a value Whether the corresponding historical reply information corresponds to at least two preset numerical ranges; the fifth determining module (not shown in the figure) is configured to respond to the historical reply information corresponding to the preset at least two numerical ranges, from the user's corresponding Determine the value range to which the value indicated by the received dialogue information belongs among the at least two value range
  • the apparatus 500 may further include: a second sending unit (not shown in the figure), configured to respond to that the preset dialogue information set does not include the target dialogue information corresponding to the user, Send the preset general reply message to the user.
  • a second sending unit (not shown in the figure), configured to respond to that the preset dialogue information set does not include the target dialogue information corresponding to the user, Send the preset general reply message to the user.
  • the first sending unit 503 may be further configured to: in response to the preset dialog information set including at least two user-corresponding target dialog information, combine the included at least two target dialog information The preset reply information corresponding to the target dialogue information that best matches the received dialogue information in the dialogue information is sent to the user.
  • the apparatus 500 may further include: a third determining unit (not shown in the figure), configured to determine a preset dialogue information set in response to determining that the user does not correspond to the historical reply information Whether it includes candidate dialogue information matching the received dialogue information; the third sending unit (not shown in the figure) is configured to respond to the preset dialogue information set including the candidate dialogue information corresponding to the user, The preset reply information corresponding to the candidate dialog information is sent to the user.
  • a third determining unit (not shown in the figure), configured to determine a preset dialogue information set in response to determining that the user does not correspond to the historical reply information Whether it includes candidate dialogue information matching the received dialogue information
  • the third sending unit (not shown in the figure) is configured to respond to the preset dialogue information set including the candidate dialogue information corresponding to the user, The preset reply information corresponding to the candidate dialog information is sent to the user.
  • the historical reply information is the last-round historical dialogue information of the reply relative to the dialogue information of the current round.
  • the apparatus 500 provided by the above-mentioned embodiment of the present disclosure may use the historical reply information sent to the user during the historical dialogue as a reference factor when replying to the dialogue information currently input by the user, and further, may comprehensively consider the dialogue information currently input by the user and the user’s dialogue information. Entering the background of the dialogue information, in this way, can answer the user more accurately and effectively, which helps to improve the accuracy and effectiveness of the man-machine dialogue.
  • FIG. 6 shows a schematic structural diagram of an electronic device (such as the terminal device or the server in FIG. 1) 600 suitable for implementing embodiments of the present disclosure.
  • Terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (e.g. Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device 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 electronic device 600 may include a processing device (such as a central processing unit, a graphics processor, etc.) 601, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 602 or from a storage device 608.
  • the program in the memory (RAM) 603 executes various appropriate actions and processing.
  • various programs and data required for the operation of the electronic device 600 are also stored.
  • the processing device 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 devices can be connected to the I/O interface 605: including input devices 606 such as touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; including, for example, liquid crystal displays (LCD), speakers, vibration An output device 607 such as a device; a storage device 608 such as a magnetic tape, a hard disk, etc.; and a communication device 609.
  • the communication device 609 may allow the electronic device 600 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 6 shows an electronic device 600 having various devices, it should be understood that it is not required to implement or have all the illustrated devices. It may alternatively be implemented or provided with more or fewer devices.
  • an embodiment of the present disclosure includes 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 device 609, or installed from the storage device 608, or installed from the ROM 602.
  • the processing device 601 the above-mentioned functions defined in the method of the embodiment 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 electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any 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 removable 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 signal 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: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs.
  • the electronic device in response to receiving the dialog information input by the user, determines whether the user corresponds to the historical reply information, Among them, the historical reply information is the historical reply to the user's historical dialogue information; in response to determining the user's corresponding historical reply information, based on the received dialogue information and the user's corresponding historical reply information, it is determined whether the preset dialogue information set includes the user's corresponding historical reply information.
  • Target dialogue information where the preset dialogue information corresponds to the preset reply information and the preset history reply information, the preset reply information is used to reply to the corresponding preset dialogue information, and the preset history reply information is used to reply to the corresponding preset
  • the historical dialogue information of the dialogue information, the target dialogue information is the preset dialogue information that matches the received dialogue information and the corresponding preset historical reply information matches the user's corresponding historical reply information; in response to the preset dialogue information set
  • the target dialogue information corresponding to the user is included, and the preset reply information corresponding to the included target dialogue information is sent to the user.
  • 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 include object-oriented programming languages—such as Java, Smalltalk, C++, and also conventional The procedural programming language-such as "C" language or similar programming language.
  • 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 may 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, and 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. Wherein, the name of the unit does not constitute a limitation on the unit itself under certain circumstances.
  • the first sending unit can also be described as "a unit for sending reply information.”

Abstract

一种用于处理信息的方法和装置。该方法包括：响应于接收到用户输入的对话信息，确定用户是否对应历史答复信息（201）；响应于用户对应历史答复信息，基于所接收的对话信息和用户对应的历史答复信息，确定预设对话信息集合是否包括用户对应的目标对话信息（202），其中，预设对话信息对应预设答复信息和预设历史答复信息，目标对话信息为与所接收的对话信息相匹配且所对应的预设历史答复信息与用户对应的历史答复信息相匹配的预设对话信息；响应于预设对话信息集合包括目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给用户（203）。可以更为准确、有效地答复用户，有助于提高人机对话的准确性和有效性。

Description

用于处理信息的方法和装置
本专利申请要求于2019年10月11日提交的、申请号为201910963496.5、申请人为京东数字科技控股有限公司、发明名称为“用于处理信息的方法和装置”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，尤其涉及用于处理信息的方法和装置。
背景技术
人机对话，是人工智能领域的一个子方向，通俗的讲就是让人可以通过人类的语言(即自然语言)与机器进行交互。作为人工智能的难题之一，一个完整的人机对话系统涉及到的技术极为广泛，例如语音处理技术、自然语言处理技术、机器学习技术等。
发明内容
本公开的实施例提出了用于处理信息的方法和装置。
第一方面，本公开的实施例提供了一种用于处理信息的方法，该方法包括：响应于接收到用户输入的对话信息，确定用户是否对应历史答复信息，其中，历史答复信息为对用户的历史对话信息的历史答复；响应于确定用户对应历史答复信息，基于所接收的对话信息和用户对应的历史答复信息，确定预设对话信息集合是否包括用户对应的目标对话信息，其中，预设对话信息对应预设答复信息和预设历史答复信息，预设答复信息用于答复对应的预设对话信息，预设历史答复信息用于答复相对于对应的预设对话信息的历史对话信息，目标对话信息为与所接收的对话信息相匹配且所对应的预设历史答复信息与用户对应的历史答复信息相匹配的预设对话信息；响应于预设对话信息集合包括目标对话信息，将所包括的目标对话信息所对应的预设答复 信息发送给用户。
在一些实施例中，基于所接收的对话信息和用户对应的历史答复信息，确定预设对话信息集合中是否包括用户对应的目标对话信息包括：确定预设对话信息集合中是否包括与所接收的对话信息相匹配的候选对话信息；响应于包括，确定所包括的候选对话信息中是否包括所对应的预设历史答复信息与用户对应的历史答复信息相匹配的目标对话信息。
在一些实施例中，预设对话信息集合包括预设数值范围对话信息，预设数值范围对话信息用于指示数值范围，预设数值范围对话信息对应的预设历史答复信息对应预设的至少两个数值范围，预设数值范围对话信息所指示的数值范围属于对应的预设历史答复信息所对应的至少两个数值范围；以及基于所接收的对话信息和用户对应的历史答复信息，确定预设对话信息集合中是否包括用户对应的目标对话信息包括：确定所接收的对话信息是否指示数值；响应于所接收的对话信息指示数值，确定用户对应的历史答复信息是否对应预设的至少两个数值范围；响应于历史答复信息对应预设的至少两个数值范围，从用户对应的历史答复信息所对应的至少两个数值范围中确定所接收的对话信息所指示的数值所属于的数值范围作为目标数值范围；确定预设对话信息集合包括的预设数值范围对话信息中是否包括所指示的数值范围与目标数值范围相匹配的候选对话信息；响应于包括，确定所包括的候选对话信息中是否包括所对应的预设历史答复信息与用户对应的历史答复信息相匹配的目标对话信息。
在一些实施例中，该方法还包括：响应于预设对话信息集合不包括用户对应的目标对话信息，将预设通用答复信息发送给用户。
在一些实施例中，响应于预设对话信息集合包括用户对应的目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给用户包括：响应于预设对话信息集合包括至少两个用户对应的目标对话信息，将所包括的至少两个目标对话信息中与所接收的对话信息最匹配的目标对话信息所对应的预设答复信息发送给用户。
在一些实施例中，该方法还包括：响应于确定用户不对应历史答 复信息，确定预设对话信息集合中是否包括与所接收的对话信息相匹配的候选对话信息；响应于预设对话信息集合包括用户对应的候选对话信息，将所包括的候选对话信息所对应的预设答复信息发送给用户。
在一些实施例中，历史答复信息为对相对于本轮的对话信息的上轮历史对话信息的答复。
第二方面，本公开的实施例提供了一种用于处理信息的装置，该装置包括：第一确定单元，被配置成响应于接收到用户输入的对话信息，确定用户是否对应历史答复信息，其中，历史答复信息为对用户的历史对话信息的历史答复；第二确定单元，被配置成响应于确定用户对应历史答复信息，基于所接收的对话信息和用户对应的历史答复信息，确定预设对话信息集合是否包括用户对应的目标对话信息，其中，预设对话信息对应预设答复信息和预设历史答复信息，预设答复信息用于答复对应的预设对话信息，预设历史答复信息用于答复相对于对应的预设对话信息的历史对话信息，目标对话信息为与所接收的对话信息相匹配且所对应的预设历史答复信息与用户对应的历史答复信息相匹配的预设对话信息；第一发送单元，被配置成响应于预设对话信息集合包括目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给用户。
第三方面，本公开的实施例提供了一种电子设备，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，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现上述用于处理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上述用于处理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处理信息的方法和装置，通过响应于接收到用户输入的对话信息，确定用户是否对应历史答复信息，其中，历史答复信息为对用户的历史对话信息的历史答复，而后响应于确定用户对应历史答复信息，基于所接收的对话信息和用户对应的历史答复信息，确定预设对话信息集合是否包括用户对应的目标对话信息， 其中，预设对话信息对应预设答复信息和预设历史答复信息，预设答复信息用于答复对应的预设对话信息，预设历史答复信息用于答复相对于对应的预设对话信息的历史对话信息，目标对话信息为与所接收的对话信息相匹配且所对应的预设历史答复信息与用户对应的历史答复信息相匹配的预设对话信息，最后响应于预设对话信息集合包括目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给用户，从而可以在答复用户当前输入的对话信息时，将历史对话过程中向用户发送的历史答复信息作为参考因素，进而，可以综合考虑用户当前输入的对话信息和用户输入对话信息的背景，以此，可以更为准确、有效地答复用户，有助于提高人机对话的准确性和有效性。
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处理信息的方法的一个实施例的流程图；
图3是根据本公开的实施例的用于处理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处理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处理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电子设备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用于处理信息的方法或用于处理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，以接收或发送消息等。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，可以是具有信息处理功能的各种电子设备，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多个软件或软件模块)，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发送的对话信息进行处理的信息处理服务器。这里，终端设备101、102、103发送的对话信息可以是用户在终端设备101、102、103上输入的对话信息。信息处理服务器可以对接收到的对话信息等数据进行分析等处理，获得处理结果(例如目标对话信息所对应的预 设答复信息)，以及信息处理服务器还可以将处理结果反馈给终端设备，以便终端设备将处理结果反馈给用户。
需要说明的是，本公开的实施例所提供的用于处理信息的方法可以由终端设备101、102、103执行，也可以由服务器105执行，相应地，用于处理信息的装置可以设置于终端设备101、102、103中，也可以设置于服务器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多个软件或软件模块)，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。
继续参考图2，示出了根据本公开的用于处理信息的方法的一个实施例的流程200。该用于处理信息的方法，包括以下步骤：
步骤201，响应于接收到用户输入的对话信息，确定用户是否对应历史答复信息。
在本实施例中，用于处理信息的方法的执行主体(例如图1所示的服务器或终端设备)可以响应于通过有线连接方式或者无线连接方式从远程或本地接收到用户输入的对话信息，确定用户是否对应历史答复信息。其中，历史答复信息为对用户的历史对话信息的历史答复。历史对话信息为在接收用户当前输入的对话信息之前用户输入的对话信息。
在本实施例的一些可选的实现方式中，历史答复信息可以用于答复相对于本轮的对话信息的上轮历史对话信息。在这里，本轮的对话信息即为当前接收到的对话信息。进而，历史答复信息即为最近一次输出的、用于答复用户的信息。可以理解，在对话过程中，前后相邻的对话信息和答复信息通常存在关联，因此，本实现方式将最近一次输出给用户的历史答复信息作为答复用户当前输入的对话信息的参 考，有助于确定出当前用户输入对话信息的前提背景，进而有助于更为有效地答复用户。作为示例，用户对应的历史答复信息可以为“为您推荐A饭店和B饭店”，当前接收的对话信息可以为“A饭店有什么特色菜”。
在本实施例中，上述对话信息(包括当前接收的对话信息和历史对话信息)可以为用户输入的、用于与机器进行对话的各种信息，包括但不限于以下至少一项：文本信息、语音信息、图像信息、视频信息。答复信息可以为用于答复对话信息的各种信息，包括但不限于以下至少一项：文本信息、语音信息、图像信息、视频信息。作为示例，对话信息可以为语音“周围有什么好吃的饭店”，对应的答复信息可以为语音“为您推荐A饭店和B饭店”。
可以理解，用户输入对话信息，上述执行主体反馈给用户相应的答复信息的过程即为人机对话的过程。
具体的，上述执行主体可以对与用户之间的对话进行记录，进而，上述执行主体可以通过对话记录，确定上述用户是否对应历史答复信息。
可选的，上述执行主体可以将用户的用户标记(例如用户ID)作为键(key)，将最近一次输出给用户的答复信息作为值(value)，以键值对的形式将用户标记和用户对应的最近一次的答复信息存储到数据库中。并且，上述执行主体还可以在每次与用户产生新的对话时，利用最新的答复信息替换数据库中存储的、该用户对应的答复信息。进而，在这里，上述执行主体可以通过确定上述数据库中是否包括用户的用户标记来确定用户是否对应历史答复信息。
步骤202，响应于确定用户对应历史答复信息，基于所接收的对话信息和用户对应的历史答复信息，确定预设对话信息集合是否包括用户对应的目标对话信息。
在本实施例中，上述执行主体可以响应于确定用户对应历史答复信息，基于所接收的对话信息和用户对应的历史答复信息，确定预设对话信息集合是否包括用户对应的目标对话信息。其中，预设对话信息对应预设答复信息和预设历史答复信息，预设答复信息用于答复对 应的预设对话信息，预设历史答复信息用于答复相对于对应的预设对话信息的历史对话信息。即预设历史答复信息为在对应的预设对话信息之前产生的、用于答复对话信息的信息。作为示例，预设对话信息可以为“C景点门票多少钱”，该预设对话信息所对应的预设历史答复信息可以为“为您推荐C景点和D景点”，该预设对话信息所对应的预设答复信息可以为“60元/人”。这里，预设历史答复信息“为您推荐C景点和D景点”可以为用于答复对话信息“M城有什么不错的景点”的信息，不难理解，对话信息“M城有什么不错的景点”为在预设对话信息“C景点门票多少钱”之前产生的对话信息，即相对于预设对话信息“C景点门票多少钱”的历史对话信息。
需要说明的是，预设对话信息以及预设对话信息所对应的预设答复信息和预设历史答复信息为预先确定的用于与用户进行对话的语料。实践中，上述执行主体可以在基于语料与用户进行对话的同时，收集产生的对话信息和答复信息，并将收集到的对话信息和答复信息作为语料，用于后续对话，以此可以使用于与用户进行对话的语料更加丰富，有助于提高人机对话的多样性。
在本实施例中，目标对话信息为与所接收的对话信息相匹配且所对应的预设历史答复信息与用户对应的历史答复信息相匹配的预设对话信息。在这里，相匹配可以指相似或相同。当相匹配指相似时，可以将相似度大于或等于预设阈值的两个信息称为相似的信息(即相匹配的信息)。其中，预设阈值可以为技术人员预先确定的数值。作为示例，预设阈值可以为0.85(相似度的取值范围为0到1)。
具体的，上述执行主体可以采用各种方法确定预设对话信息集合是否包括用户所对应的目标对话信息。
在本实施例的一些可选的实现方式中，上述执行主体可以首先确定预设对话信息集合中是否包括与所接收的对话信息相匹配的候选对话信息。这里，候选对话信息即为与所接收的对话信息相匹配的预设对话信息。然后，上述执行主体可以响应于确定预设对话信息集合中包括与所接收的对话信息相匹配的候选对话信息，确定所包括的候选对话信息中是否包括所对应的预设历史答复信息与用户对应的历史答 复信息相匹配的目标对话信息。
本实现方式可以采用逐步筛选的方式确定目标对话信息，即首先基于对话信息的匹配确定候选对话信息，然后基于历史答复信息的匹配，从候选对话信息中确定目标对话信息，相对于直接从预设对话信息集合中查找同时满足对话信息匹配和历史答复信息匹配两个条件的预设对话信息，本实现方式可以减小确定目标对话信息的工作量，有助于减小答复用户过程中所消耗的资源，提高答复用户的效率。
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响应于确定用户不对应历史答复信息，确定预设对话信息集合中是否包括与所接收的对话信息相匹配的候选对话信息，以及响应于预设对话信息集合包括用户对应的候选对话信息，将所包括的候选对话信息所对应的预设答复信息发送给用户。
步骤203，响应于预设对话信息集合包括目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给用户。
在本实施例中，上述执行主体可以响应于预设对话信息集合包括用户对应的目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给用户。
具体的，若上述执行主体直接与用户交互，则上述执行主体可以直接输出目标对话信息所对应的预设答复信息；若上述执行主体通过用户终端与用户交互，则上述执行主体可以将目标对话信息所对应的预设答复信息发送用户所使用的用户终端，以便用户终端将接收的预设答复信息输出给用户。
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响应于预设对话信息集合不包括用户对应的目标对话信息，将预设通用答复信息发送给用户。这里，预设通用答复信息为预先设置的、用于在无法从预设的语料中找到用于答复用户的预设答复信息时，对用户做出回应。作为示例，预设通用答复信息可以为“不好意思，我还没有学会如何回答这个问题，您可以转接人工服务”。
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响应于预设对话信息集合包括至少两个用户对应的目标对话信息，将所包 括的至少两个目标对话信息中与所接收的对话信息最匹配的目标对话信息所对应的预设答复信息发送给用户。这里，最匹配的目标对话信息可以为与所接收的对话信息的相似度最高的目标对话信息；也可以为对应的预设历史答复信息与用户对应的历史答复信息的相似度最高的目标对话信息；或者，也可以为对话信息(目标对话信息和所接收的对话信息)的相似度与历史答复信息(目标对话信息对应的预设历史答复信息和用户对应的历史答复信息)的相似度的均值最大的目标对话信息。
继续参见图3，图3是根据本实施例的用于处理信息的方法的应用场景的一个示意图。
在图3的应用场景中，首先，手机301可以响应于接收到用户302输入的对话信息303(例如“A饭店的特色是什么”)，确定用户302是否对应历史答复信息，其中，历史答复信息为对用户302的历史对话信息的历史答复。
然后，手机301可以响应于确定用户302对应历史答复信息304(例如“这里为您推荐好吃A饭店和B饭店”，作为示例，“这里为您推荐好吃A饭店和B饭店”可以为对用户的历史对话信息“请帮忙推荐一下甲城市的饭店”的答复)，基于所接收的对话信息303和用户302对应的历史答复信息304，确定预设对话信息集合305是否包括用户302对应的目标对话信息，其中，预设对话信息对应预设答复信息和预设历史答复信息，预设答复信息用于答复对应的预设对话信息，预设历史答复信息用于答复相对于对应的预设对话信息的历史对话信息，目标对话信息为与所接收的对话信息303相匹配且所对应的预设历史答复信息与用户302对应的历史答复信息304相匹配的预设对话信息。
接着，手机301可以响应于预设对话信息集合305包括用户302对应的目标对话信息306(例如“A饭店的特色菜是什么”)，将所包括的目标对话信息306所对应的预设答复信息307(例如“锅包肉”)发送给用户302。
本公开的上述实施例提供的方法可以在答复用户当前输入的对话信息时，将历史对话过程中向用户发送的历史答复信息作为参考因素，进而，可以综合考虑用户当前输入的对话信息和用户输入对话信息的背景，以此，可以更为准确、有效地答复用户，有助于提高人机对话的准确性和有效性。
进一步参考图4，其示出了用于处理信息的方法的又一个实施例的流程400。该用于处理信息的方法的流程400，包括以下步骤：
步骤401，响应于接收到用户输入的对话信息，确定用户是否对应历史答复信息。
在本实施例中，用于处理信息的方法的执行主体(例如图1所示的服务器或终端设备)可以响应于通过有线连接方式或者无线连接方式从远程或本地接收到用户输入的对话信息，确定用户是否对应历史答复信息。其中，历史答复信息为对用户的历史对话信息的历史答复。历史对话信息为在接收用户当前输入的对话信息之前用户输入的对话信息。
步骤402，响应于确定用户对应历史答复信息，确定所接收的对话信息是否指示数值。
在本实施例中，上述执行主体可以响应于确定用户对应历史答复信息，确定步骤401中接收到的对话信息是否指示数值。作为示例，接收到的对话信息可以为“身高170cm”，则该对话信息可以指示数值170；或者，接收到的对话信息可以为“我今年21岁”，则该对话信息可以指示数值“21”。
步骤403，响应于所接收的对话信息指示数值，确定用户对应的历史答复信息是否对应预设的至少两个数值范围。
在本实施例中，上述执行主体可以响应于所接收的对话信息指示数值，确定用户对应的历史答复信息是否对应预设的至少两个数值范围。
可以理解，实践中，用于答复用户的答复信息为预先设置的信息，而针对用于获取用户输入的具体特征(例如身高特征、年龄特征等) 的特征值的答复信息，技术人员还可以针对该答复信息预先设置至少两个数值范围，以便在用户输入不同的特征值后，针对特征值所属的数值范围，选择不同的答复信息进行答复。需要说明的是，针对答复信息预先设置的至少两个数值范围可以为互斥的至少两个数值范围。
作为示例，历史答复信息可以为“请问您的身高是多少”，针对该历史答复信息，可以预先设置三个数值范围(即至少两个数值范围)，分别为“[150,160]；[160,170]；[170,180]”，进而当用户输入对话信息“我身高165”时，可以选择[160,170]对应的答复信息“建议您选择M码”输出给用户；当用户输入对话信息“我身高155”时，可以选择[150,160]对应的答复信息“建议您选择S码”输出给用户；当用户输入对话信息“我身高175”时，可以选择[170,180]对应的答复信息“建议您选择L码”输出给用户。
需要说明的是，这里示例性地给出了答复用户输入的、用于指示数值的对话信息的总过程，具体如何将对话信息与数值范围对应、如何确定对应出的数值范围所对应的答复信息等内容将在后续步骤中进行详细描述。
步骤404，响应于历史答复信息对应预设的至少两个数值范围，从用户对应的历史答复信息所对应的至少两个数值范围中确定所接收的对话信息所指示的数值所属于的数值范围作为目标数值范围。
在本实施例中，上述执行主体可以响应于历史答复信息对应预设的至少两个数值范围，从用户对应的历史答复信息所对应的至少两个数值范围中确定所接收的对话信息所指示的数值所属于的数值范围作为目标数值范围。继续上述示例，用户输入的对话信息可以为“我身高155”，历史答复信息“请问您的身高是多少”可以对应三个数值范围，分别为“[150,160]；[160,170]；[170,180]”，则由于对话信息“我身高155”所指示的数值155属于数值范围[150,160]，则可以将数值范围[150,160]确定为目标数值范围。
实践中，通常会对答复信息和答复信息对应的至少两个数值范围进行关联存储。在这里，数值范围可以以各种形式存储，例如可以以图形的形式存储，或者以布尔表达式的形式存储。可以理解，当数值 范围以布尔表达式的形式存储时，目标数值范围即为将对话信息所指示的数值代入布尔表达式后，为真的布尔表达式所对应的数值范围。
步骤405，确定预设对话信息集合包括的预设数值范围对话信息中是否包括所指示的数值范围与目标数值范围相匹配的候选对话信息。
在本实施例中，预设对话信息集合包括预设数值范围对话信息，预设数值范围对话信息用于指示数值范围，预设数值范围对话信息对应的预设历史答复信息对应预设的至少两个数值范围，预设数值范围对话信息所指示的数值范围属于对应的预设历史答复信息所对应的至少两个数值范围，进而基于步骤404中获得的目标数值范围，上述执行主体可以确定预设对话信息集合包括的预设数值范围对话信息中是否包括所指示的数值范围与目标数值范围相匹配的候选对话信息。这里，相匹配可以指相同或相似。
在本实施例中，预设数值范围对话信息可以为用于指示数值范围的各种信息，包括但不限于以下至少一项：文字、数字、符号、图像，音频、视频。
步骤406，响应于包括，确定所包括的候选对话信息中是否包括所对应的预设历史答复信息与用户对应的历史答复信息相匹配的目标对话信息。
在本实施例中，上述执行主体可以响应于确定预设对话信息集合包括的预设数值范围对话信息中包括所指示的数值范围与目标数值范围相匹配的候选对话信息，确定所包括的候选对话信息中是否包括所对应的预设历史答复信息与用户对应的历史答复信息相匹配的目标对话信息。
继续上述示例，目标数值范围为[150,160]，预设对话信息中可以包括预设数值范围对话信息“身高在150cm至160cm之间”和预设数值范围对话信息“体重在150斤至160斤之间”，可以看出，这两个预设数值范围对话信息均指示数值范围[150,160]，与目标数值范围相同(即相匹配)，进而上述执行主体可以将这两个预设数值范围对话信息确定为候选对话信息。以及，用户对应的历史答复信息可以为“请问 您的身高是多少”，而确定出的候选对话信息“身高在150cm至160cm之间”所对应的预设历史答复信息可以为“请问您的身高是多少”；候选对话信息“体重在150斤至160斤之间”所对应的预设历史答复信息可以为“请问您的体重是多少”，则由于候选对话信息“身高在150cm至160cm之间”所对应的预设历史答复信息与用户所对应的历史答复信息相同(即相匹配)，所以上述执行主体可以确定候选对话信息中包括所对应的预设历史答复信息与用户对应的历史答复信息相匹配的目标对话信息，即“身高在150cm至160cm之间”。
可以理解，当用户的对话信息指示数值时，基于对话信息与预设对话信息相似或相同的方法将较难用于目标对话信息的确定。具体的，一方面，在设置预设对话信息集合时，难以穷举出所有用户可能输入的数值；另一方面，即使指示数值的两个对话信息在形式上相似度较大，但只要这两个对话信息所指示的数值不同，则这两个对话信息的实际意义则可能大不相同。例如，对于对话信息“我今年8岁”和对话信息“我今年80岁”，虽然这两个对话信息相似，但实际意义却相去甚远。因此，本实施例采用了将接收的对话信息所指示的数值表征为目标数值范围，进而基于数值范围的匹配确定目标对话信息的方法，以此，可以提高对用户输入的、与数值相关的对话信息进行答复的有效性。
步骤407，响应于候选对话信息中包括目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给用户。
在本实施例中，上述执行主体可以响应于候选对话信息中包括所对应的预设历史答复信息与用户对应的历史答复信息相匹配的目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给用户。
上述步骤401和步骤407可以分别采用与前述实施例中的步骤201和步骤203类似的方式执行，上文针对步骤201和步骤203的描述也适用于步骤401和步骤407，此处不再赘述。
从图4中可以看出，与图2对应的实施例相比，本实施例中的用于处理信息的方法的流程400突出了在用户输入的对话信息指示数值的情况下，基于对话信息所指示的数值所属的目标数值范围，从预设 对话信息中匹配目标对话信息的步骤。由此，本实施例描述的方案可以实现针对用户输入的、与数值相关的对话信息的答复，提高了人机对话的适用性和多样性。
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处理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，该装置具体可以应用于各种电子设备中。
如图5所示，本实施例的用于处理信息的装置500包括：第一确定单元501、第二确定单元502和第一发送单元503。其中，第一确定单元501被配置成响应于接收到用户输入的对话信息，确定用户是否对应历史答复信息，其中，历史答复信息为对用户的历史对话信息的历史答复；第二确定单元502被配置成响应于确定用户对应历史答复信息，基于所接收的对话信息和用户对应的历史答复信息，确定预设对话信息集合是否包括用户对应的目标对话信息，其中，预设对话信息对应预设答复信息和预设历史答复信息，预设答复信息用于答复对应的预设对话信息，预设历史答复信息用于答复相对于对应的预设对话信息的历史对话信息，目标对话信息为与所接收的对话信息相匹配且所对应的预设历史答复信息与用户对应的历史答复信息相匹配的预设对话信息；第一发送单元503被配置成响应于预设对话信息集合包括目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给用户。
在本实施例中，用于处理信息的装置500的第一确定单元501可以响应于通过有线连接方式或者无线连接方式从远程或本地接收到用户输入的对话信息，确定用户是否对应历史答复信息。其中，历史答复信息为对用户的历史对话信息的历史答复。历史对话信息为在接收用户当前输入的对话信息之前用户输入的对话信息。
在本实施例中，第二确定单元502可以响应于确定用户对应历史答复信息，基于所接收的对话信息和用户对应的历史答复信息，确定预设对话信息集合是否包括用户对应的目标对话信息。其中，预设对话信息对应预设答复信息和预设历史答复信息，预设答复信息用于答 复对应的预设对话信息，预设历史答复信息用于答复相对于对应的预设对话信息的历史对话信息。即预设历史答复信息为在对应的预设对话信息之前产生的、用于答复对话信息的信息。
在本实施例中，目标对话信息为与所接收的对话信息相匹配且所对应的预设历史答复信息与用户对应的历史答复信息相匹配的预设对话信息。在这里，相匹配可以指相似或相同。
在本实施例中，第一发送单元503可以响应于预设对话信息集合包括用户对应的目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给用户。
在本实施例的一些可选的实现方式中，第二确定单元502可以包括：第一确定模块(图中未示出)，被配置成确定预设对话信息集合中是否包括与所接收的对话信息相匹配的候选对话信息；第二确定模块(图中未示出)，被配置成响应于包括，确定所包括的候选对话信息中是否包括所对应的预设历史答复信息与用户对应的历史答复信息相匹配的目标对话信息。
在本实施例的一些可选的实现方式中，预设对话信息集合包括预设数值范围对话信息，预设数值范围对话信息用于指示数值范围，预设数值范围对话信息对应的预设历史答复信息对应预设的至少两个数值范围，预设数值范围对话信息所指示的数值范围属于对应的预设历史答复信息所对应的至少两个数值范围；以及第二确定单元502可以包括：第三确定模块(图中未示出)，被配置成确定所接收的对话信息是否指示数值；第四确定模块(图中未示出)，被配置成响应于所接收的对话信息指示数值，确定用户对应的历史答复信息是否对应预设的至少两个数值范围；第五确定模块(图中未示出)，被配置成响应于历史答复信息对应预设的至少两个数值范围，从用户对应的历史答复信息所对应的至少两个数值范围中确定所接收的对话信息所指示的数值所属于的数值范围作为目标数值范围；第六确定模块(图中未示出)，被配置成确定预设对话信息集合包括的预设数值范围对话信息中是否包括所指示的数值范围与目标数值范围相匹配的候选对话信息；第七确定模块(图中未示出)，被配置成响应于包括，确定所包括的候选对 话信息中是否包括所对应的预设历史答复信息与用户对应的历史答复信息相匹配的目标对话信息。
在本实施例的一些可选的实现方式中，装置500还可以包括：第二发送单元(图中未示出)，被配置成响应于预设对话信息集合不包括用户对应的目标对话信息，将预设通用答复信息发送给用户。
在本实施例的一些可选的实现方式中，第一发送单元503可以进一步被配置成：响应于预设对话信息集合包括至少两个用户对应的目标对话信息，将所包括的至少两个目标对话信息中与所接收的对话信息最匹配的目标对话信息所对应的预设答复信息发送给用户。
在本实施例的一些可选的实现方式中，装置500还可以包括：第三确定单元(图中未示出)，被配置成响应于确定用户不对应历史答复信息，确定预设对话信息集合中是否包括与所接收的对话信息相匹配的候选对话信息；第三发送单元(图中未示出)，被配置成响应于预设对话信息集合包括用户对应的候选对话信息，将所包括的候选对话信息所对应的预设答复信息发送给用户。
在本实施例的一些可选的实现方式中，历史答复信息为对答复相对于本轮的对话信息的上轮历史对话信息。
可以理解的是，该装置500中记载的诸单元与参考图2描述的方法中的各个步骤相对应。由此，上文针对方法描述的操作、特征以及产生的有益效果同样适用于装置500及其中包含的单元，在此不再赘述。
本公开的上述实施例提供的装置500可以在答复用户当前输入的对话信息时，将历史对话过程中向用户发送的历史答复信息作为参考因素，进而，可以综合考虑用户当前输入的对话信息和用户输入对话信息的背景，以此，可以更为准确、有效地答复用户，有助于提高人机对话的准确性和有效性。
下面参考图6，其示出了适于用来实现本公开实施例的电子设备(例如图1中的终端设备或服务器)600的结构示意图。本公开实施例中的终端设备可以包括但不限于诸如移动电话、笔记本电脑、数字 广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图6示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图6所示，电子设备600可以包括处理装置(例如中央处理器、图形处理器等)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装置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，还存储有电子设备600操作所需的各种程序和数据。处理装置601、ROM 602以及RAM603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。
通常，以下装置可以连接至I/O接口605：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置606；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置607；包括例如磁带、硬盘等的存储装置608；以及通信装置609。通信装置609可以允许电子设备600与其他设备进行无线或有线通信以交换数据。虽然图6示出了具有各种装置的电子设备600，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
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装置609从网络上被下载和安装，或者从存储装置608被安装，或者从ROM 602被安装。在该计算机程序被处理装置601执行时，执行本公开实施例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，该计算机可读信号介质可以发送、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：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。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电子设备执行时，使得该电子设备：响应于接收到用户输入的对话信息，确定用户是否对应历史答复信息，其中，历史答复信息为对用户的历史对话信息的历史答复；响应于确定用户对应历史答复信息，基于所接收的对话信息和用户对应的历史答复信息，确定预设对话信息集合是否包括用户对应的目标对话信息，其中，预设对话信息对应预设答复信息和预设历史答复信息，预设答复信息用于答复对应的预设对话信息，预设历史答复信息用于答复相对于对应的预设对话信息的历史对话信息，目标对话信息为与所接收的对话信息相匹配且所对应的预设历史答复信息与用户对应的历史答复信息相匹配的预设对话信息；响应于预设对话信息集合包括用户对应的目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给用户。
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对象的程序设计语言—诸如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。其中，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，第一发送单元还可以被描述为“发送答复信息的单元”。
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，本公开中所涉及的公开范围，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公开构思的情况下，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 (10)

  1. 一种用于处理信息的方法，包括：
    响应于接收到用户输入的对话信息，确定所述用户是否对应历史答复信息，其中，历史答复信息为对所述用户的历史对话信息的历史答复；
    响应于确定所述用户对应历史答复信息，基于所接收的对话信息和所述用户对应的历史答复信息，确定预设对话信息集合是否包括所述用户对应的目标对话信息，其中，预设对话信息对应预设答复信息和预设历史答复信息，预设答复信息用于答复对应的预设对话信息，预设历史答复信息用于答复相对于对应的预设对话信息的历史对话信息，目标对话信息为与所接收的对话信息相匹配且所对应的预设历史答复信息与所述用户对应的历史答复信息相匹配的预设对话信息；
    响应于所述预设对话信息集合包括目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给所述用户。
  2. 根据权利要求1所述的方法，其中，所述基于所接收的对话信息和所述用户对应的历史答复信息，确定预设对话信息集合中是否包括所述用户对应的目标对话信息包括：
    确定所述预设对话信息集合中是否包括与所接收的对话信息相匹配的候选对话信息；
    响应于所述预设对话信息集合中包括与所接收的对话信息相匹配的候选对话信息，确定所包括的候选对话信息中是否包括所对应的预设历史答复信息与所述用户对应的历史答复信息相匹配的目标对话信息。
  3. 根据权利要求1所述的方法，其中，所述预设对话信息集合包括预设数值范围对话信息，预设数值范围对话信息用于指示数值范围，预设数值范围对话信息对应的预设历史答复信息对应预设的至少两个数值范围，预设数值范围对话信息所指示的数值范围属于对应的预设 历史答复信息所对应的至少两个数值范围；以及
    所述基于所接收的对话信息和所述用户对应的历史答复信息，确定预设对话信息集合中是否包括所述用户对应的目标对话信息包括：
    确定所接收的对话信息是否指示数值；
    响应于所接收的对话信息指示数值，确定所述用户对应的历史答复信息是否对应预设的至少两个数值范围；
    响应于历史答复信息对应预设的至少两个数值范围，从所述用户对应的历史答复信息所对应的至少两个数值范围中确定所接收的对话信息所指示的数值所属于的数值范围作为目标数值范围；
    确定所述预设对话信息集合包括的预设数值范围对话信息中是否包括所指示的数值范围与所述目标数值范围相匹配的候选对话信息；
    响应于所述预设对话信息集合包括的预设数值范围对话信息中包括所指示的数值范围与所述目标数值范围相匹配的候选对话信息，确定所包括的候选对话信息中是否包括所对应的预设历史答复信息与所述用户对应的历史答复信息相匹配的目标对话信息。
  4. 根据权利要求1所述的方法，其中，所述方法还包括：
    响应于预设对话信息集合不包括所述用户对应的目标对话信息，将预设通用答复信息发送给所述用户。
  5. 根据权利要求1所述的方法，其中，所述响应于所述预设对话信息集合包括所述用户对应的目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给所述用户包括：
    响应于所述预设对话信息集合包括至少两个所述用户对应的目标对话信息，将所包括的至少两个目标对话信息中与所接收的对话信息最匹配的目标对话信息所对应的预设答复信息发送给所述用户。
  6. 根据权利要求1所述的方法，其中，所述方法还包括：
    响应于确定所述用户不对应历史答复信息，确定所述预设对话信息集合中是否包括与所接收的对话信息相匹配的候选对话信息；
    响应于所述预设对话信息集合包括所述用户对应的候选对话信息，将所包括的候选对话信息所对应的预设答复信息发送给所述用户。
  7. 根据权利要求1-6之一所述的方法，其中，历史答复信息为相对于本轮的对话信息的上轮历史对话信息的历史答复。
  8. 一种用于处理信息的装置，包括：
    第一确定单元，被配置成响应于接收到用户输入的对话信息，确定所述用户是否对应历史答复信息，其中，历史答复信息为对所述用户的历史对话信息的历史答复；
    第二确定单元，被配置成响应于确定所述用户对应历史答复信息，基于所接收的对话信息和所述用户对应的历史答复信息，确定预设对话信息集合是否包括所述用户对应的目标对话信息，其中，预设对话信息对应预设答复信息和预设历史答复信息，预设答复信息用于答复对应的预设对话信息，预设历史答复信息用于答复相对于对应的预设对话信息的历史对话信息，目标对话信息为与所接收的对话信息相匹配且所对应的预设历史答复信息与所述用户对应的历史答复信息相匹配的预设对话信息；
    第一发送单元，被配置成响应于所述预设对话信息集合包括目标对话信息，将所包括的目标对话信息所对应的预设答复信息发送给所述用户。
  9. 一种电子设备，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。
  10. 一种计算机可读介质，其上存储有计算机程序，其中，该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/CN2020/088369 2019-10-11 2020-04-30 用于处理信息的方法和装置 WO2021068493A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US17/767,262 US20220391425A1 (en) 2019-10-11 2020-04-30 Method and apparatus for processing information
EP20874910.1A EP4044044A4 (en) 2019-10-11 2020-04-30 METHOD AND DEVICE FOR PROCESSING INFORMATION

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910963496.5A CN110727775B (zh) 2019-10-11 2019-10-11 用于处理信息的方法和装置
CN201910963496.5 2019-10-11

Publications (1)

Publication Number Publication Date
WO2021068493A1 true WO2021068493A1 (zh) 2021-04-15

Family

ID=69220984

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/088369 WO2021068493A1 (zh) 2019-10-11 2020-04-30 用于处理信息的方法和装置

Country Status (4)

Country Link
US (1) US20220391425A1 (zh)
EP (1) EP4044044A4 (zh)
CN (1) CN110727775B (zh)
WO (1) WO2021068493A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113268609A (zh) * 2021-06-22 2021-08-17 中国平安人寿保险股份有限公司 基于知识图谱的对话内容推荐方法、装置、设备及介质
CN113569029A (zh) * 2021-07-28 2021-10-29 北京小米移动软件有限公司 对话应答方法、装置及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110727775B (zh) * 2019-10-11 2021-03-30 京东数字科技控股有限公司 用于处理信息的方法和装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130232204A1 (en) * 2012-03-01 2013-09-05 International Business Machines Corporation Identifying and processing previously sent and received messages
CN109344242A (zh) * 2018-09-28 2019-02-15 广东工业大学 一种对话问答方法、装置、设备及存储介质
CN110019742A (zh) * 2018-06-19 2019-07-16 北京京东尚科信息技术有限公司 用于处理信息的方法和装置
CN110222159A (zh) * 2019-04-30 2019-09-10 电子科技大学 一种基于文本的人机交互训练方法及系统
CN110309283A (zh) * 2019-06-28 2019-10-08 阿里巴巴集团控股有限公司 一种智能问答的答案确定方法及装置
CN110727775A (zh) * 2019-10-11 2020-01-24 京东数字科技控股有限公司 用于处理信息的方法和装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8082151B2 (en) * 2007-09-18 2011-12-20 At&T Intellectual Property I, Lp System and method of generating responses to text-based messages
US11144602B2 (en) * 2017-08-31 2021-10-12 International Business Machines Corporation Exploiting answer key modification history for training a question and answering system
US11188838B2 (en) * 2018-01-30 2021-11-30 Salesforce.Com, Inc. Dynamic access of artificial intelligence engine in a cloud computing architecture
CN110309275A (zh) * 2018-03-15 2019-10-08 北京京东尚科信息技术有限公司 一种对话生成的方法和装置
CN110083693B (zh) * 2019-04-28 2021-03-12 腾讯科技（深圳）有限公司 机器人对话回复方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130232204A1 (en) * 2012-03-01 2013-09-05 International Business Machines Corporation Identifying and processing previously sent and received messages
CN110019742A (zh) * 2018-06-19 2019-07-16 北京京东尚科信息技术有限公司 用于处理信息的方法和装置
CN109344242A (zh) * 2018-09-28 2019-02-15 广东工业大学 一种对话问答方法、装置、设备及存储介质
CN110222159A (zh) * 2019-04-30 2019-09-10 电子科技大学 一种基于文本的人机交互训练方法及系统
CN110309283A (zh) * 2019-06-28 2019-10-08 阿里巴巴集团控股有限公司 一种智能问答的答案确定方法及装置
CN110727775A (zh) * 2019-10-11 2020-01-24 京东数字科技控股有限公司 用于处理信息的方法和装置

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113268609A (zh) * 2021-06-22 2021-08-17 中国平安人寿保险股份有限公司 基于知识图谱的对话内容推荐方法、装置、设备及介质
CN113268609B (zh) * 2021-06-22 2023-12-01 中国平安人寿保险股份有限公司 基于知识图谱的对话内容推荐方法、装置、设备及介质
CN113569029A (zh) * 2021-07-28 2021-10-29 北京小米移动软件有限公司 对话应答方法、装置及存储介质

Also Published As

Publication number Publication date
EP4044044A1 (en) 2022-08-17
CN110727775B (zh) 2021-03-30
EP4044044A4 (en) 2023-10-04
CN110727775A (zh) 2020-01-24
US20220391425A1 (en) 2022-12-08

Similar Documents

Publication Publication Date Title
WO2021068493A1 (zh) 用于处理信息的方法和装置
CN109993150B (zh) 用于识别年龄的方法和装置
US9686133B2 (en) Establishment of connection channels between complementary agents
US20130110992A1 (en) Electronic device management using interdomain profile-based inferences
WO2020228416A1 (zh) 一种应答方法和装置
WO2020207174A1 (zh) 用于生成量化神经网络的方法和装置
US20200167429A1 (en) Efficient use of word embeddings for text classification
US11526681B2 (en) Dynamic multilingual speech recognition
US11783808B2 (en) Audio content recognition method and apparatus, and device and computer-readable medium
US20230088445A1 (en) Conversational recommendation method, method of training model, device and medium
EP4297030A2 (en) Polling questions for a conference call discussion
CN112650841A (zh) 信息处理方法、装置和电子设备
US10318639B2 (en) Intelligent action recommendation
JP2023550211A (ja) テキストを生成するための方法および装置
CN110008926B (zh) 用于识别年龄的方法和装置
US20190188623A1 (en) Cognitive and dynamic business process generation
US11120223B2 (en) Probabilistic word embeddings for text classification
CN110059172B (zh) 基于自然语言理解的推荐答案的方法和装置
CN112182255A (zh) 用于存储媒体文件和用于检索媒体文件的方法和装置
CN112149699A (zh) 用于生成模型的方法、装置和用于识别图像的方法、装置
CN116863935B (zh) 语音识别方法、装置、电子设备与计算机可读介质
CN110335237B (zh) 用于生成模型的方法、装置和用于识别图像的方法、装置
CN111435381A (zh) 请求分发方法和装置
US20230046881A1 (en) Intelligent meeting recording using artificial intelligence algorithms
CN111339770B (zh) 用于输出信息的方法和装置

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: 20874910

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020874910

Country of ref document: EP

Effective date: 20220511