CN115906808A - Method, device, medium and computing device for confirming speech response degree - Google Patents
Method, device, medium and computing device for confirming speech response degree Download PDFInfo
- Publication number
- CN115906808A CN115906808A CN202211479123.9A CN202211479123A CN115906808A CN 115906808 A CN115906808 A CN 115906808A CN 202211479123 A CN202211479123 A CN 202211479123A CN 115906808 A CN115906808 A CN 115906808A
- Authority
- CN
- China
- Prior art keywords
- session
- text
- determining
- session text
- responsiveness
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Transfer Between Computers (AREA)
Abstract
Embodiments of the present disclosure provide a talk response confirmation method, apparatus, medium, and computing device, where the method includes: respectively determining the session responsiveness of each session text in a target group chat session according to a responsiveness function, wherein each session text respectively corresponds to information of a sender, and the sender comprises group chat members in the target group chat session; and classifying the conversation response degree of the conversation text based on the information of the sender so as to obtain the corresponding speaking response degree of each group chat member in the target group chat conversation. According to the method and the device, the speaking response degree of the group chat members is accurately determined through the response degree function.
Description
Technical Field
Embodiments of the present disclosure relate to the field of chat, and more particularly, to a method, an apparatus, a medium, and a computing device for confirming a speech responsiveness.
Background
This section is intended to provide a background or context to the embodiments of the disclosure. The description herein is not admitted to be prior art by inclusion in this section.
Group chat has become a common way for multiple people to communicate. Group chat refers to three or more people participating in a chat.
During group chat, the utterance of some members is followed by other members and is actively responded to. The influence of the members is significantly better than that of other members, and the activities can be pushed to the members in commerce, so that the popularization of the activities is realized based on the influence of the members.
In an exemplary technique, the influence of a member is determined by calculating the level of talk response of the member in the group chat. The degree of talk response refers to the strength with which the member's talk is responded to by other members in the group chat. The speaking response degree is obtained by calculating the speaking times of the members and the speaking times of other members after the members speak each time. But the utterances of the other members are not necessarily responses to the utterance of the current member, resulting in inaccurate calculation of the utterance responsiveness of the members.
Disclosure of Invention
The present disclosure provides a speech response degree confirmation method, apparatus, medium, and computing device, which are used to solve the problem that the computation of the speech response degree of a member is inaccurate.
In a first aspect of the disclosed embodiments, there is provided a speech responsiveness confirmation method, including: respectively determining the session responsiveness of each session text in a target group chat session according to a responsiveness function, wherein each session text respectively corresponds to information of a sender, and the sender comprises group chat members in the target group chat session; and classifying the conversation response degree of the conversation text based on the information of the sender so as to obtain the corresponding speaking response degree of each group chat member in the target group chat conversation.
In an embodiment of the present disclosure, the determining session responsiveness of each session text in the target group chat session according to the responsiveness function includes: determining the scope of the first session text, and determining each second session text positioned in the scope; respectively constructing a response function of the first session text and each second session text; determining the score of a response function corresponding to the second session text according to the first session text and the second session text; and determining the conversation responsiveness of the first conversation text according to the scores corresponding to the responsiveness functions.
In another embodiment of the present disclosure, the determining, according to the first session text and the second session text, a score of a response degree function corresponding to the second session text includes: and in response to the second session text comprising first content replying to the first session text, determining the set maximum number as the score of the responsiveness function corresponding to the second session text.
In another embodiment of the present disclosure, the first content includes an identifier of a sender corresponding to the first session text, and/or the first content includes directional characters of the sender replying to the first session text.
In another embodiment of the present disclosure, the determining, according to the first session text and the second session text, a score of a response degree function corresponding to the second session text includes: and in response to the second session text comprising second content replying to other session texts, determining the set minimum value as the value of the corresponding response degree function of the second session text, wherein the other session texts are session texts except the first session text.
In another embodiment of the present disclosure, the second content includes an identifier of another sender, and/or the second content includes a directional character replying to the other sender, where the other sender is a member of the group chat except for the sender corresponding to the first session text.
In another embodiment of the present disclosure, the determining, according to the first session text and the second session text, a score of a response degree function corresponding to the second session text includes: in response to the second session text not including the first content replying to the first session text, determining a relevance parameter of the second session text to the first session text; and determining the score of the response function corresponding to the second session text according to the correlation parameter.
In another embodiment of the present disclosure, the determining the correlation parameter between the second session text and the first session text includes: adding the first conversation text to the front of the second conversation text to obtain a first word and sentence; adding the second conversation text to the front of the first conversation text to obtain a second word and sentence; and determining the correlation parameters of the second conversation text and the first conversation text according to the first words and the second words.
In another embodiment of the present disclosure, the determining the correlation parameter of the second conversation text and the first conversation text according to the first word sentence and the second word sentence includes determining a first probability value between each first word in the first word sentence and a corresponding first sentence, the first sentence corresponding to the first word being a sentence before the first word, the first probability value being used for indicating a semantic smoothness degree of the first sentence; determining a second probability value between each second word in the second sentence and a corresponding second sentence, wherein the second sentence corresponding to the second word is a sentence before the second word, and the second probability value is used for indicating the semantic smoothness of the second sentence;
and determining a first total probability value of the first sentence according to each first probability value, and determining a second total probability value of the second sentence according to each second probability value, wherein the correlation parameters comprise the first total probability value and the second total probability value.
In another embodiment of the present disclosure, the determining a score of a response function corresponding to the second session text according to the relevance parameter includes: in response to the first total probability value being greater than or equal to the second total probability value, determining a difference value between the first total probability value and the second total probability value as a score of a responsiveness function corresponding to the second conversational text; and in response to the first total probability value being smaller than or equal to the second total probability value, determining a set minimum number value as a score of a responsiveness function corresponding to the second session text.
In another embodiment of the present disclosure, the determining the scope of the first session text comprises: and determining a scope of the first session text according to a next session text of the first session text, the maximum reply quantity of the first session text or the maximum reply duration of the first session text, wherein the next session text and the first session text are adjacent session texts of a sender speaking corresponding to the first session text.
In another embodiment of the present disclosure, the determining the scope of the first session text includes: and in response to the fact that no conversation text exists between the next text and the first conversation text, determining the scope of the next text as the scope of the first conversation text, wherein the next conversation text and the first conversation text are adjacent conversation texts of a sender speaking corresponding to the first conversation text.
In a second aspect of the disclosed embodiments, there is also provided a speech responsiveness confirmation apparatus including: the determining module is used for respectively determining the session responsiveness of each session text in the target group chat session according to the responsiveness function, each session text corresponds to the information of a sender, and the sender comprises group chat members in the target group chat session; and the processing module is used for classifying the conversation response degree of the conversation text based on the information of the sender so as to obtain the speaking response degree corresponding to each group chat member in the target group chat conversation.
In an embodiment of the present disclosure, the determining module includes: the determining unit is used for determining the scope of the first session text and determining each second session text positioned in the scope; the construction unit is used for respectively constructing the response degree functions of the first session text and the second session texts; the determining unit is further configured to determine, according to the first session text and the second session text, a score of a response degree function corresponding to the second session text; the determining unit is further configured to determine a session responsiveness of the first session text according to the score corresponding to each responsiveness function.
In another embodiment of the present disclosure, the determining unit includes: and a first determining subunit, configured to determine, in response to that the second session text includes a first content replying to the first session text, the set maximum number as a score of a responsiveness function corresponding to the second session text.
In another embodiment of the present disclosure, the first content includes an identifier of a sender corresponding to the first session text, and/or the first content includes directional characters of the sender replying to the first session text.
In another embodiment of the present disclosure, the determining unit includes: and a second determining subunit, configured to determine, in response to that the second session text includes second content replying to other session texts, the set minimum number value as a score of a responsiveness function corresponding to the second session text, where the other session texts are session texts other than the first session text.
In another embodiment of the present disclosure, the second content includes an identification of other senders, and/or the second content includes directional characters replying to the other senders, which are members of the group chat except the sender corresponding to the first session text.
In another embodiment of the present disclosure, the determining unit includes: a third determining subunit, configured to determine a relevance parameter of the second session text and the first session text in response to that the second session text does not include the first content replied to the first session text; the third determining subunit is further configured to determine, according to the relevance parameter, a score of a response degree function corresponding to the second session text.
In another embodiment of the present disclosure, the third determining subunit includes, including: the adding subunit is configured to add the first session text to the front of the second session text to obtain a first word and sentence; the adding subunit is configured to add the second session text to the front of the first session text, so as to obtain a second word and sentence; and the determining component is used for determining the correlation parameters of the second conversation text and the first conversation text according to the first words and the second words.
In another embodiment of the present disclosure, the determining component includes a determining component for determining a first probability value between each first word in the first sentence and a corresponding first sentence, the first sentence corresponding to the first word being a sentence preceding the first word, the first probability value being used to indicate a semantic smoothness of the first sentence; the determining component is further configured to determine a second probability value between each second word in the second sentence and a corresponding second sentence, where the second sentence corresponding to the second word is a sentence before the second word, and the second probability value is used to indicate a semantic smoothness of the second sentence; the determining unit is further configured to determine a first total probability value of the first sentence according to each first probability value, and determine a second total probability value of the second sentence according to each second probability value, where the correlation parameter includes the first total probability value and the second total probability value.
In another embodiment of the present disclosure, the determining means includes: the determining module is used for determining a difference value between the first total probability value and the second total probability value as a score of a response function corresponding to the second session text in response to the first total probability value being greater than or equal to the second total probability value; and the determining module is further used for determining the set minimum number value as the score of the response degree function corresponding to the second session text in response to the first total probability value being smaller than or equal to the second total probability value.
In another embodiment of the present disclosure, the determining unit includes: a fourth determining subunit, configured to determine a scope of the first session text according to a next session text of the first session text, the maximum reply quantity of the first session text, or the maximum reply duration of the first session text, where the next session text and the first session text are adjacent session texts of the sender speaking corresponding to the first session text.
In another embodiment of the present disclosure, the determining unit includes: and a fifth determining subunit, configured to determine, in response to that there is no session text between the next text and the first session text, a scope of the next text as a scope of the first session text, where the next session text and the first session text are adjacent session texts spoken by a sender corresponding to the first session text.
In a third aspect of the disclosed embodiments, there is also provided a medium comprising: computer-executable instructions for implementing the talk-back confirmation method as described above when executed by a processor.
In a third aspect of the disclosed embodiments, there is also provided a computing device comprising:
a memory and a processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored by the memory to cause the processor to perform a talk-back confirmation method as described above.
In the embodiment of the disclosure, the session responsiveness of each session text in the group chat session is determined through the responsiveness function, and then the session responsiveness of the session text is classified through the information of the sender of the session text, so that the speaking responsiveness of each group chat member in the group chat session is obtained, that is, the speaking responsiveness of the group chat members is accurately determined through the responsiveness function.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
fig. 1 schematically illustrates an application scenario diagram of a speech responsiveness confirmation method according to an embodiment of the present disclosure;
FIG. 2 schematically shows a flow diagram according to an embodiment of the present disclosure;
FIG. 3 schematically shows a flow diagram according to another embodiment of the present disclosure;
FIG. 4 schematically shows a flow diagram according to yet another embodiment of the disclosure;
FIG. 5 schematically illustrates a flow diagram according to yet another embodiment of the disclosure;
FIG. 6 schematically shows a flow diagram according to yet another embodiment of the disclosure;
FIG. 7 schematically shows a schematic diagram of a program product provided according to an embodiment of the disclosure;
fig. 8 is a schematic structural diagram illustrating an utterance responsiveness confirmation apparatus provided according to an embodiment of the present disclosure;
fig. 9 schematically illustrates a structural diagram of a computing device provided according to an embodiment of the present disclosure.
In the drawings, like or corresponding reference numerals designate like or corresponding parts.
Detailed Description
The principles and spirit of the present disclosure will be described below with reference to several exemplary embodiments. It is understood that these embodiments are given solely for the purpose of enabling those skilled in the art to better understand and to practice the present disclosure, and are not intended to limit the scope of the present disclosure in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be embodied as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.
According to the embodiment of the disclosure, a speech responsiveness confirming method, a speech responsiveness confirming device, a speech responsiveness confirming apparatus, a speech responsiveness confirming medium and a computing apparatus are provided.
Moreover, any number of elements in the drawings are by way of example and not by way of limitation, and any nomenclature is used solely for differentiation and not by way of limitation.
In addition, the data related to the present disclosure may be data authorized by a user or fully authorized by each party, and the collection, transmission, use, and the like of the data all meet the requirements of relevant national laws and regulations, and the embodiments/examples of the present disclosure may be combined with each other.
The principles and spirit of the present disclosure are explained in detail below with reference to several representative embodiments of the present disclosure.
Summary of The Invention
During group chat, the utterance of some members is followed by other members and is actively responded to. The influence of the members is significantly better than that of other members, and the activities can be pushed to the members in commerce, so that the popularization of the activities is realized based on the influence of the members.
The inventor of the present disclosure finds that the influence of the member is determined by calculating the speech response of the member in the group chat. The degree of talk response refers to the strength with which the member's talk is responded to by other members in the group chat. The speaking response degree is obtained by calculating the speaking times of the members and the speaking times of other members after the members speak every time. But the utterances of other members are not necessarily responses to the utterance of the current member, resulting in inaccurate calculation of the utterance responsiveness of the members.
The inventor of the present disclosure therefore thinks that the conversation responsiveness of each conversation text in the group chat session is determined through the responsiveness function, and then the conversation responsiveness of the conversation text is classified and processed through the information of the sender of the conversation text, so as to obtain the speaking responsiveness of each group chat member in the group chat session, that is, the speaking responsiveness of the group chat members is accurately determined through the responsiveness function.
Application scene overview
Referring to fig. 1, fig. 1 is a schematic view of an application scenario of a speech responsiveness determining method according to an embodiment of the disclosure. As shown in fig. 1, the terminal device 100 intercepts a group chat session 200, where the group chat session 200 includes utterances of a plurality of group chat members, each utterance corresponds to a session text, and the session text includes information of a sender, where the information of the sender refers to an identifier such as a name of a group chat member. Illustratively, group chat session 200 includes 5 session texts, session text 1 is "forest XX: big family good! "the conversation text 2 is" horse X: you are good and me is good. ", session text 3 is" king X: everybody is really in the air. ", session text 4 is" butyl X: +1", session text 5 is" forest XX: people are well known, wherein the "forest XX", "Ding X", "horse X" and "Wang X" are the information of the sender. The terminal device 100 constructs a response function based on each session text, thereby determining the session response of each session text through the response function, and then classifies the session response of each session text based on the information of the sender to obtain the speaking response of the group chat members.
Exemplary method
A talk back confirmation method according to an exemplary embodiment of the present disclosure is described below with reference to fig. 2 to 6 in conjunction with the application scenario of fig. 1. It should be noted that the above application scenarios are merely illustrated for the convenience of understanding the spirit and principles of the present disclosure, and the embodiments of the present disclosure are not limited in this respect. Rather, embodiments of the present disclosure may be applied to any scenario where applicable.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating an embodiment of a method for confirming a speech responsiveness according to an embodiment of the present disclosure, where the method includes:
step S201, according to the response function, determining the session response of each session text in the target group chat session, wherein each session text corresponds to the information of a sender, and the sender comprises the group chat members in the target group chat session.
In the present embodiment, the execution subject is an utterance degree response confirmation apparatus, and for convenience of description, the apparatus is hereinafter referred to as an utterance degree response confirmation apparatus. The apparatus may be any terminal device having data processing capabilities, for example, the apparatus may be a computer.
The device can provide a chat function for a plurality of terminal devices, namely, each terminal device realizes the chat among a plurality of users by taking the device as a center. A chat between multiple users is defined as a group chat session. The apparatus determines a target group chat session from a plurality of group chat sessions, which may be in a randomly determined manner, i.e., randomly determined among the plurality of group chat sessions. Or, the device monitors that a certain user has certain influence, the device needs to accurately determine the speaking response degree of the user, and the group chat session including the user is determined as the target group chat session.
The target group chat session comprises a plurality of session texts, wherein the session texts refer to words or voices of the target group chat members speaking in the group chat, the session texts comprise information of a sender, the sender is the group chat members in the target group chat session, and the information of the sender comprises identification of the group chat members, such as name or image of the group chat members and other information representing unique identities of the group chat members.
The device constructs a responsiveness function based on each piece of session text. Illustratively, the response function is R (1,2), 1 and 2 are the sequence numbers of the session texts in the target group chat session, 1 represents the session text with sequence number 1, and 2 represents the session text with sequence number 2.
The device can calculate the conversation responsiveness of each conversation text based on the responsiveness function. Exemplarily, if three session texts with sequence numbers of 1,2 and 3 are included in the target group chat session text, response degree functions R (1,2), R (1,3) and R (2,3) are constructed, and if a session text with a subsequent sequence number is a response text of a session text with a previous sequence number, the speech response degree of the session text with the previous sequence number is M; and if the session text with the subsequent sequence number is not the response text of the session text with the previous sequence number, the speaking response degree of the session text with the previous sequence number is N, and M is greater than N. For example, the session text 1 is: "Lin XX: horse X, never see a pymetropia ", the session text 2 is: "horse X: yes, forest XX ", then the conversation text 2 is the response text of the conversation text 1; if the session text 1 is: "Lin XX: horse X, never see a pymetropia ", the session text 2 is: "Wang X: today's weather is good ", the conversation text 2 is not a response text to the conversation text 1.
Illustratively, the function of the degree of response is R (1,2), and if the session text with sequence number 2 is the response text of the session text with sequence number 1, the session degree of response of the session text with sequence number 1 is 1; if the session text with the sequence number 2 is not the response text of the session text with the sequence number 1, the session response degree of the session text with the sequence number 1 is 0.
Step S202, based on the information of the sender, the conversation response degree of the conversation text is classified to obtain the speaking response degree corresponding to each group chat member in the target group chat conversation.
The device determines the conversation response degree of each conversation text, and then the speaking response degrees of the members in the group need to be calculated. The device can classify the conversation response degree of the conversation text based on the information of the sender, and then the speaking response degree corresponding to the group chat members can be obtained.
In an example, each session text corresponds to a sender, the device determines each session text belonging to the same sender, the sum of the session responses of each session text is the speech response of the sender, and the speech response of the sender is the speech response of the group chat members.
The device calculates the speaking response degree of each group chat member in the target group chat session, determines the group chat member with the speaking response degree larger than a preset threshold value as a target user, and can push information to the target user. The pushed information can be information such as commodities or advertisements. The speaking response degree of the target user is higher, the receiving degree of the target user recommending the goods or the advertisements to other users is higher, and the popularization range of the goods or the advertisements is expanded by utilizing the speaking response degree of the target user.
In this embodiment, the session responsiveness of each session text in the group chat session is determined through the responsiveness function, and then the session responsiveness of the session text is classified through information of a sender of the session text, so as to obtain the speech responsiveness of each group chat member in the group chat session, that is, the speech responsiveness of the group chat members is accurately determined through the responsiveness function.
Referring to fig. 3, fig. 3 is a schematic flowchart illustrating another embodiment of the utterance responsiveness confirmation method according to an embodiment of the present disclosure, and based on the embodiment illustrated in fig. 2, step S201 includes:
step S301, determining the scope of the first session text, and determining each second session text located in the scope.
In this embodiment, each session text has a corresponding scope. Scope refers to the effective reply duration of the session text or the effective reply text.
The preset duration after the sending time point of the session text can be used as an effective reply duration, and the preset duration can be any composite number. Or, the interval duration between the transmission time points of the adjacent two session texts of the group chat members is the effective reply duration.
A preset number of session texts with speaking positions behind the session texts can be used as effective response texts, for example, 10 session texts speaking behind the session text 1 can be used as effective response texts of the session text 1, and for example, other session texts between two adjacent session texts of group chat members are effective response texts.
In an example, the apparatus determines the first session text scope based on a next session text of the first session text, a maximum number of replies to the first session text, or a maximum reply duration for the first session text. The next session text is adjacent session text of the sender to which the first session text corresponds. Illustratively, user a speaks a conversation text 1 first and then speaks a conversation text 2, where conversation text 1 is the first conversation text and conversation text 2 is the next conversation text. It will be appreciated that there are at least three ways to determine the scope of the first session text described above.
In particular, the device may scope the first session text to the next session text, i.e. the scope of the first session text is the session text between the first session text and the next session text. In addition, the device may use the maximum number of replies after the first session text as the scope of the first session text, where the maximum number of replies is the preset number. In addition, the device may use the maximum reply duration of the first session text as the scope of the first session text, where the maximum reply duration is the preset duration.
In another example, the group chat member may speak a plurality of session texts continuously, and there is no session text spoken by other users between the plurality of session texts, and the apparatus regards the plurality of session texts spoken continuously by the group chat member as one session text. When determining the scope of a plurality of session texts which are continuously spoken by the group chat members, determining the scope of the session text which is spoken by the group chat members last, and determining the scope of each session text which is continuously spoken by the group chat members. For example, if the user a continuously speaks the conversation text 1, the conversation text 2, and the conversation text 3, the scope of the conversation text 3 is defined as the scope of the conversation texts 1 and 2. It will be appreciated that there is no conversation text between the next text and the first conversation text, and the scope of the next text is determined to be the scope of the first conversation text. It should be noted that, when the utterance responsiveness of the session text is calculated, if the group chat member utters a plurality of session texts continuously, the session texts are integrated to be the first session text, and then the scope of the first session text is adopted to determine the session responsiveness of the first session text.
The apparatus determines a session text located within the scope of the first session text as a second session text corresponding to the first session text. For example, the session texts between the adjacent session texts of the group chat members are taken as the respective second session texts. As another example, 10 pieces of session text located after the first session text are taken as the second session text. For another example, a conversation text spoken in a preset time period is taken as the conversation text, a starting time point of the preset time period is a speaking time point of the first conversation text, and the preset duration is a total duration of the preset time period.
Step S302, respectively constructing a response function between the first session text and each of the second session texts.
And defining the session text of which the speaking response degree needs to be calculated currently as a first session text, and defining the session text behind the first session text as a second session text, namely, a plurality of second session texts exist. The apparatus constructs a responsiveness function of the first session text with each of the second session texts. Illustratively, the target group chat session texts include three session texts with sequence numbers of 1,2 and 3, the first session text is session text 1, the second session texts are session text 2 and session text 3, and the response degree functions constructed by the first session text and each second session text are R (1,2) and R (1,3).
Step S303, determining a score of the response degree function corresponding to the second session text according to the first session text and the second session text.
And the device constructs a response function, and calculates the score of the response function corresponding to the first conversation text and the second conversation text.
In an example, if the second session text includes the first content in reply to the first session text, the set maximum value is determined as the score of the responsiveness function corresponding to the second session text. The first content comprises an identification of a sender to which the first session text corresponds and/or the first content comprises directional characters of the sender in reply to the first session text. The identifier of the sender may be a name of a group chat member of the first session text, for example, if the sender of the first session text is "forest XX", and if the second session text includes the content of "forest XX", it may be determined that the second session text includes the first content replied to the first session text. For example, the directional character is @, for example, the sender of the first session text is "forest XX", and if the second session text includes the content of "@ forest XX", it may be determined that the second session text includes the first content of replying to the first session text. The maximum value set may be any suitable value, for example a maximum value of 1.
In another example, if the second session text includes a second content replying to other session texts, the set minimum value is determined as the score of the responsiveness function corresponding to the second session text. The other senders are members of the group chat except the sender corresponding to the first session text. For example, if the sender of the first session text is "forest XX", and the second session text includes "horse X", the "horse X" is the sender of the other session text. The second content includes an identification of a sender corresponding to the other session text and/or the second content includes directional characters of the sender in reply to the other session text. The identifier of the sender may be names of group chat members of other session texts, for example, if the sender of the first session text is "forest XX", and if the second session text includes the content of "horse X", it may be determined that the second session text includes the second content replying to the other session text. For example, the directional character is @, for example, the sender of the first session text is "forest XX", and if the other session text includes the content of "@ horse X", it may be determined that the second session text includes the second content replying to the other session text. The minimum value set may be any suitable value, for example a minimum value of 0.
Step S304, determining the conversation responsiveness of the first conversation text according to the scores corresponding to the responsiveness functions.
And each second session text corresponding to the first session text has a score of the corresponding response function, and the scores are added to obtain the session response of the first session text.
In this embodiment, the apparatus determines the respective second session texts corresponding to the first session texts based on the scope of the first session texts, so as to accurately determine the session responsiveness of the first session texts based on the responsiveness function of the first session texts and each second session text.
Referring to fig. 4, fig. 4 is a schematic flowchart illustrating a flowchart of another embodiment of an utterance responsiveness confirmation method according to an embodiment of the present disclosure, where based on the embodiment illustrated in fig. 3, step S303 includes:
step S401, in response to that the second session text does not include the first content replied to the first session text, determining a correlation parameter between the second session text and the first session text.
In this embodiment, the apparatus cannot definitely determine that the second session text is the responsiveness of the first session text. For example, the first session text is "I have played a new game today" and the second session text is "downloading". If the second session text does not include the content explicitly replying to the first session text, the device cannot determine whether the second session text is the reply text of the first session text.
In this regard, the apparatus calculates a correlation parameter between the second session text and the first session text upon detecting that the second session text does not include the first content in reply to the first session text. For the first content, reference is made to the above description, and details are not repeated herein.
In an example, the apparatus may convert the first conversation text into a first word vector and the second conversation text into a second word vector, and calculate a distance between the first word vector and the second word vector, which may be used as a correlation parameter between the first conversation text and the second conversation text.
Step S402, determining the score of the response function corresponding to the second session text according to the relevance parameter.
The device determines the relation parameters of the first conversation text and the second conversation text, namely, the score of the response function of the second conversation text can be determined.
In an example, if the relevance parameter is greater than a preset value, determining the set maximum value as a score of a response function corresponding to the second session text; and if the relevant system parameters are less than or equal to the preset values, determining the set minimum value as the score of the response function corresponding to the second session text.
In another example, the device may determine the score of the response function corresponding to the second session text based on the relationship parameter and the mapping relationship, and the larger the relationship parameter is, the larger the score of the response function is.
In this embodiment, if the second session text does not include the first content replying to the first session text, the correlation parameter between the first session text and the second session text is determined, so that the score of the response degree function corresponding to the second session text is accurately determined according to the correlation parameter.
Referring to fig. 5, fig. 5 is a schematic flowchart illustrating a flowchart of a further embodiment of an utterance responsiveness confirmation method according to an embodiment of the present disclosure, where based on the embodiment illustrated in fig. 4, step S402 includes:
step S501, adding the first session text to the front of the second session text to obtain the first word and sentence.
Step S502, adding the second conversation text in front of the first conversation text to obtain a second word and sentence.
The second conversation text is the response text of the first conversation text, the content of the second conversation text is connected behind the first conversation text and is a sentence with smooth semantics, and the content of the first conversation text is connected behind the second conversation text and is possibly a sentence with unsmooth voice.
In this regard, the apparatus adds the first conversational text to the second conversational text to obtain a first word and adds the second conversational text to the first conversational text to obtain a second word.
Step S503, determining a correlation parameter between the second session text and the first session text according to the first word and the second word.
The apparatus may determine a correlation parameter of the second session text with the first session text according to the first words and the second words. Specifically, the device performs semantic detection on the first words and sentences and the second words and sentences respectively to obtain numerical values with smooth semantics respectively. If the value of the first word and sentence with smooth semantics is larger than the preset value and the value of the second word and sentence with smooth semantics is smaller than the preset value, determining that the semantics of the first word and sentence are smooth and the semantics of the second word and sentence are not smooth, namely determining that the second conversation text is the response text of the first conversation text, and setting the correlation parameters of the first word and the second word and sentence as larger values; and if the value of the smooth semantics of the first word and sentence is smaller than the preset value, and no matter whether the value of the smooth semantics of the second word and sentence is larger than or smaller than the preset value, determining that the second conversation text is not the response text of the first conversation text, wherein the correlation parameter of the first conversation text and the second conversation text is a smaller value.
In this embodiment, the device obtains the first word and the second word by linking the contents of the first conversation text and the second conversation text in different orders, so as to accurately determine the relation parameter between the first conversation text and the second conversation text based on the first word and the second word.
Referring to fig. 6, fig. 6 is a flowchart illustrating an example of a flow chart of a further embodiment of the method for acknowledging a talk back according to the embodiment of the present disclosure, based on the embodiment illustrated in fig. 5, step S503 includes:
step S601, determining a first probability value between each first word in the first sentence and the corresponding first sentence, where the first sentence corresponding to the first word is a sentence before the first word, and the first probability value is used to indicate a semantic smoothness degree of the first sentence.
In this embodiment, the apparatus obtains the first word and the second word, and determines the semantic smoothness of the first word through the relationship between words in the first word and the second word.
Specifically, the device determines a first probability value between each first word in the first sentence and the corresponding first sentence, wherein the first sentence corresponding to the first word is the sentence before the first word, and the first probability value is used for indicating the semantic smoothness degree of the first sentence.
Illustratively, the first expression is "tomorrow is monday and is going to again", the first word is "bright", and there is no statement before the first word is "bright", then a first probability value P (bright | < beginning of text >) = a0 corresponding to "bright", and a0 is a first preset value; and the first word is "day", and the first sentence of "day" is "bright", then the first probability value P (day | < bright >) = a1 corresponding to "day", a1 is obtained by semantic detection of "day" and "bright" by the language model set in the device. And so on. When the first word is "go", then "go" corresponds to the first probability value P (go | < tomorrow is monday, also >) = a9.
Step S602, determining a second probability value between each second word in the second sentence and the corresponding second sentence, where the second sentence corresponding to the second word is a sentence before the second word, and the second probability value is used to indicate a semantic smoothness of the second sentence.
The device determines a second probability value between each second word in the second sentence and the corresponding second sentence, wherein the second sentence corresponding to the second word is the sentence before the second word, and the second probability value is used for indicating the semantic smoothness of the second sentence.
Illustratively, the second word is "go again, tomorrow is monday", the second word is "again", and there is no sentence before "again", then a second probability value P corresponding to "again" (again | < beginning of word >) = b0, and b0 is a second preset value; and the second word is "want", and the second sentence of "want" is "again", then "want" corresponding second probability value P (want | < again >) = b1, b1 is detected semantically by the language model set up in the device to "want" and "again". And so on. When the second word is "yes", then "the corresponding second probability value P (i < go, tomorrow is monday >) = b9 is" reached ".
Step S603, determining a first total probability value of the first sentence according to each first probability value, and determining a second total probability value of the second sentence according to each second probability value, where the correlation parameter includes a first total probability value and a second total probability value.
After the first probability values corresponding to the first characters in the first words and sentences are obtained, the device calculates a first total probability value of the first words and sentences. For example, the first probability values corresponding to the first words may be multiplied to obtain a first total probability value. For example, the first word "tomorrow is monday, and then" is to be removed ", and the first total probability value P (tomorrow is monday, and then) is = P (tomorrow < text start >) > P (day | < tomorrow >) > P (tomorrow >) P (tomorrow | < tomorrow is >)) P (one | < tomorrow is week >) P (which is monday >) (again | < tomorrow is monday), P (which is monday, again >) (to | < tomorrow is monday, again >) (to be monday is monday, again >)) P (to be" | < tomorrow is monday, again >).
And after the second probability values corresponding to the second words in the second words and sentences are obtained, the device calculates the second total probability values of the second words and sentences. For example, the second probability values corresponding to the second words may be multiplied to obtain the second total probability value. For example, the second word is "go again, tomorrow is monday", the second total probability value P (go again, tomorrow is monday) = P (again, | < text start >) P (again, | < again >), < go >) P (bright > < go again >) (day > < go again, bright >) (is, < go again, bright >) P (week > < go again, bright day >) P (week >) (is, < go again, bright day is week >) (is < go again, bright day is week >)).
The device obtains a correlation parameter between the first session text and the second session text based on the first total probability value and the second total probability value, that is, the correlation parameter includes the first total probability value and the second total probability value.
Further, the apparatus needs to determine a responsiveness value corresponding to the second dialog text based on the first total probability value and the second total probability value. Specifically, the first total probability value represents the semantic smoothness of the first word and sentence, and the second total probability value represents the semantic smoothness of the second word and sentence. If the second session text is reply text of the first session text, the first total probability value is greater than the second total probability value. Therefore, the score of the response function corresponding to the second session text may refer to the following formula:
wherein P (1,2) is a first total probability value, P (2,1) is a second total probability value, 1 represents a first session text, 2 represents a second session text, and R (1,2) is a responsiveness function of the first session text and the second session text. And if the first total probability value is greater than or equal to the second total probability value, determining the score corresponding to the response degree function as the difference between the first total probability value and the second total probability value, namely determining the difference as the score of the response degree function corresponding to the second session text. And if the first total probability value is smaller than the second total probability value, determining the set minimum value as the score of the response function corresponding to the second session text, wherein the minimum value is 0 in the formula.
It should be noted that the larger the score corresponding to the response degree function is, the more likely the second session text is to be the response text of the first session text.
In this embodiment, the apparatus determines a first total probability value of the first word and sentence through each first probability value of the first word and sentence, and determines a second total probability value of the second word and sentence based on each second probability value of the second word and sentence, so as to accurately determine a relation parameter between the first conversation text and the second conversation text through the first total probability value and the second total probability value.
Exemplary Medium
Having described the method of the exemplary embodiment of the present disclosure, next, a storage medium of the exemplary embodiment of the present disclosure will be described with reference to fig. 7.
Referring to fig. 7, a storage medium 70 stores a program product for implementing the above method according to an embodiment of the present disclosure, which may employ a portable compact disc read only memory (CD-ROM) and includes computer-executable instructions for causing a computing device to perform the talk-back confirmation method provided by the present disclosure. However, the program product of the present disclosure is not limited thereto.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A readable signal medium may include a propagated data signal with computer-executable instructions embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. The readable signal medium may also be any readable medium other than a readable storage medium.
Computer-executable instructions for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer executable instructions may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN).
Exemplary devices
Having described the media of the exemplary embodiments of the present disclosure, next, a speech responsiveness confirmation apparatus of the exemplary embodiments of the present disclosure will be described with reference to fig. 7, which is used to implement the method in any of the speech responsiveness confirmation method embodiments described above, and the implementation principle and technical effects thereof are similar.
Referring to fig. 8, fig. 8 schematically illustrates a structural diagram of an utterance responsiveness confirmation apparatus provided in accordance with an embodiment of the present disclosure.
As shown in fig. 8, the utterance responsiveness confirmation apparatus includes: a determining module 810, configured to determine session responsiveness of each session text in the target group chat session according to the responsiveness function, where each session text corresponds to information of a sender, and the sender includes group chat members in the target group chat session; the processing module 820 is configured to classify the session response degrees of the session texts based on the information of the sender, so as to obtain utterance response degrees corresponding to each group chat member in the target group chat session.
In an embodiment, the determining module 810 includes: the determining unit is used for determining the scope of the first session text and determining each second session text positioned in the scope; the construction unit is used for respectively constructing the response degree functions of the first session texts and the second session texts; the determining unit is further used for determining the score of the response degree function corresponding to the second conversation text according to the first conversation text and the second conversation text; and the determining unit is also used for determining the conversation responsiveness of the first conversation text according to the scores corresponding to the responsiveness functions.
In an embodiment, the determining unit comprises: and the first determining subunit is used for determining the set maximum value as the value of the corresponding response degree function of the second session text in response to the second session text comprising the first content replying to the first session text.
In an embodiment, the first content comprises an identification of a sender to which the first session text corresponds, and/or the first content comprises directional characters of the sender in reply to the first session text.
In an embodiment, the determining unit comprises: and a second determining subunit, configured to determine, in response to that the second session text includes second content replying to other session texts, the set minimum number value as a score of a responsiveness function corresponding to the second session text, where the other session texts are session texts other than the first session text.
In an embodiment, the second content comprises an identification of the other sender, and/or the second content comprises a directional character replying to the other sender, the other sender being a member of the group chat other than the sender to which the first session text corresponds.
In an embodiment, the determining unit comprises: a third determining subunit, configured to determine, in response to that the second session text does not include the first content replied to the first session text, a correlation parameter between the second session text and the first session text; and the third determining subunit is further configured to determine, according to the correlation parameter, a score of the response degree function corresponding to the second session text.
In an embodiment, the third determining subunit includes, including: the adding subunit is used for adding the first session text in front of the second session text to obtain a first word and sentence; the adding subunit is used for adding the second session text in front of the first session text to obtain a second word and sentence; and the determining component is used for determining the correlation parameters of the second conversation text and the first conversation text according to the first words and the second words.
In one embodiment, a determination component comprises: determining means for determining a first probability value between each first word in the first sentence and the corresponding first sentence, the first sentence corresponding to the first word being a sentence preceding the first word, the first probability value being used to indicate a semantic smoothness of the first sentence; the determining component is further used for determining a second probability value between each second word in the second sentence and the corresponding second sentence, the second sentence corresponding to the second word is the sentence before the second word, and the second probability value is used for indicating the semantic smoothness of the second sentence; the determining component is further used for determining a first total probability value of the first sentence according to each first probability value, determining a second total probability value of the second sentence according to each second probability value, and the correlation parameter comprises a first total probability value and a second total probability value.
In one embodiment, the determining means comprises: the determining module is used for determining the difference value of the first total probability value and the second total probability value as the score of the response function corresponding to the second session text in response to the fact that the first total probability value is larger than or equal to the second total probability value; and the determining module is further used for determining the set minimum number value as the score of the response degree function corresponding to the second session text in response to the first total probability value being smaller than or equal to the second total probability value.
In one embodiment, the determining unit 810 includes: and the fourth determining subunit is configured to determine the scope of the first session text according to a next session text of the first session text, the maximum reply number of the first session text, or the maximum reply duration of the first session text, where the next session text and the first session text are adjacent session texts spoken by the sender corresponding to the first session text.
In one embodiment, the determining unit 810 includes: and a fifth determining subunit, configured to determine, in response to that no session text exists between the next text and the first session text, a scope of the next text as a scope of the first session text, where the next session text and the first session text are adjacent session texts spoken by a sender corresponding to the first session text.
Exemplary computing device
Having described the method, medium, and utterance responsiveness confirmation apparatus of the exemplary embodiments of the present disclosure, a computing device of the exemplary embodiments of the present disclosure is described next with reference to fig. 9.
The computing device 90 shown in fig. 9 is only one example and should not impose any limitations on the functionality or scope of use of embodiments of the disclosure. As shown in fig. 9, computing device 90 is embodied in the form of a general purpose computing device. Components of computing device 90 may include, but are not limited to: at least one processing unit 901, at least one memory unit 902, and a bus 903 that couples various system components including the processing unit 901 and the memory unit 902. Wherein computer executable instructions are stored in the at least one memory unit 902; the at least one processing unit 901 comprises a processor executing the computer executable instructions to implement the above described method.
The bus 903 includes a data bus, a control bus, and an address bus.
The storage unit 902 may include readable media in the form of volatile memory, such as a Random Access Memory (RAM) 9021 and/or a cache memory 9022, and may further include readable media in the form of non-volatile memory, such as a Read Only Memory (ROM) 9023.
It should be noted that although in the above detailed description several units/modules or sub-units/modules of the utterance responsiveness confirmation device are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module, in accordance with embodiments of the present disclosure. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.
Further, while the operations of the disclosed methods are depicted in the drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
While the spirit and principles of the present disclosure have been described with reference to several particular embodiments, it is to be understood that the present disclosure is not limited to the particular embodiments disclosed, nor is the division of aspects, which is for convenience only as the features in such aspects may not be combined to benefit. The disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (10)
1. A speech responsiveness confirmation method, comprising:
respectively determining the session responsiveness of each session text in a target group chat session according to a responsiveness function, wherein each session text respectively corresponds to information of a sender, and the sender comprises group chat members in the target group chat session;
and classifying the conversation response degree of the conversation text based on the information of the sender so as to obtain the corresponding speaking response degree of each group chat member in the target group chat conversation.
2. The method for confirming speech responsiveness according to claim 1, wherein the determining the session responsiveness of each session text in the target group chat session according to the responsiveness function comprises:
determining the scope of the first session text, and determining each second session text positioned in the scope;
respectively constructing a response function of the first session text and each second session text;
determining a score of a response degree function corresponding to the second session text according to the first session text and the second session text;
and determining the conversation responsiveness of the first conversation text according to the scores corresponding to the responsiveness functions.
3. The method for confirming speech responsiveness according to claim 2, wherein the determining a score of the responsiveness function corresponding to the second session text according to the first session text and the second session text comprises:
and in response to the second session text comprising first content replying to the first session text, determining the set maximum number as the score of the corresponding response degree function of the second session text.
4. The method for confirming the responsiveness to speech according to claim 2, wherein the determining, from the first session text and the second session text, a score of a responsiveness function corresponding to the second session text comprises:
and in response to the second session text comprising second content replying to other session texts, determining the set minimum value as the value of the corresponding response degree function of the second session text, wherein the other session texts are session texts except the first session text.
5. The method for confirming speech responsiveness according to claim 2, wherein the determining a score of the responsiveness function corresponding to the second session text according to the first session text and the second session text comprises:
in response to the second session text not including the first content replying to the first session text, determining a relevance parameter of the second session text to the first session text;
and determining the score of the response function corresponding to the second session text according to the correlation parameter.
6. The method of claim 5, wherein the determining the correlation parameter between the second session text and the first session text comprises:
adding the first conversation text to the front of the second conversation text to obtain a first word and sentence;
adding the second conversation text to the front of the first conversation text to obtain a second word and sentence;
and determining the correlation parameters of the second conversation text and the first conversation text according to the first words and the second words.
7. The method of claim 6, wherein the determining the correlation parameter between the second conversational text and the first conversational text from the first word and the second word comprises
Determining a first probability value between each first word in the first sentence and a corresponding first sentence, wherein the first sentence corresponding to the first word is a sentence before the first word, and the first probability value is used for indicating the semantic smoothness degree of the first sentence;
determining a second probability value between each second word in the second sentence and a corresponding second sentence, wherein the second sentence corresponding to the second word is a sentence before the second word, and the second probability value is used for indicating the semantic smoothness of the second sentence;
and determining a first total probability value of the first word and sentence according to each first probability value, and determining a second total probability value of the second word and sentence according to each second probability value, wherein the correlation parameters comprise the first total probability value and the second total probability value.
8. An utterance responsiveness confirmation apparatus, comprising:
the determining module is used for respectively determining the session responsiveness of each session text in the target group chat session according to the responsiveness function, each session text corresponds to the information of a sender, and the sender comprises group chat members in the target group chat session;
and the processing module is used for classifying the conversation response degree of the conversation text based on the information of the sender so as to obtain the speaking response degree corresponding to each group chat member in the target group chat conversation.
9. A medium, comprising: computer-executable instructions for implementing the utterance responsiveness confirmation method according to any one of claims 1 to 7 when executed by a processor.
10. A computing device, comprising:
a memory and a processor;
the memory stores computer-executable instructions;
the processor executing the computer-executable instructions stored by the memory causes the processor to perform the utterance responsiveness confirmation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211479123.9A CN115906808A (en) | 2022-11-23 | 2022-11-23 | Method, device, medium and computing device for confirming speech response degree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211479123.9A CN115906808A (en) | 2022-11-23 | 2022-11-23 | Method, device, medium and computing device for confirming speech response degree |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115906808A true CN115906808A (en) | 2023-04-04 |
Family
ID=86480059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211479123.9A Pending CN115906808A (en) | 2022-11-23 | 2022-11-23 | Method, device, medium and computing device for confirming speech response degree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115906808A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117892711A (en) * | 2023-12-11 | 2024-04-16 | 中新金桥数字科技(北京)有限公司 | Method for obtaining text correlation based on large model |
-
2022
- 2022-11-23 CN CN202211479123.9A patent/CN115906808A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117892711A (en) * | 2023-12-11 | 2024-04-16 | 中新金桥数字科技(北京)有限公司 | Method for obtaining text correlation based on large model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11727941B2 (en) | Managing dialog data providers | |
| KR102381214B1 (en) | Man-machine dialogue method, device and electronic equipment | |
| KR102297394B1 (en) | Automated assistant invocation of appropriate agent | |
| CN109961792B (en) | Method and apparatus for recognizing speech | |
| US8265933B2 (en) | Speech recognition system for providing voice recognition services using a conversational language model | |
| JP7566789B2 (en) | Two-pass end-to-end speech recognition | |
| US20130144619A1 (en) | Enhanced voice conferencing | |
| AU2019219717B2 (en) | System and method for analyzing partial utterances | |
| US9361589B2 (en) | System and a method for providing a dialog with a user | |
| CN109284502B (en) | Text similarity calculation method and device, electronic equipment and storage medium | |
| CN110415679A (en) | Voice error correction method, device, equipment and storage medium | |
| US11605385B2 (en) | Project issue tracking via automated voice recognition | |
| CN112818109B (en) | Intelligent reply method, medium, device and computing equipment for mail | |
| US10785270B2 (en) | Identifying or creating social network groups of interest to attendees based on cognitive analysis of voice communications | |
| US11776563B2 (en) | Textual echo cancellation | |
| KR101891498B1 (en) | Method, computer device and computer readable recording medium for multi domain service resolving the mixture of multi-domain intents in interactive ai agent system | |
| CN108055617A (en) | Microphone awakening method and device, terminal equipment and storage medium | |
| CN111462726B (en) | Method, device, equipment and medium for answering out call | |
| CN115906808A (en) | Method, device, medium and computing device for confirming speech response degree | |
| KR20190074508A (en) | Method for crowdsourcing data of chat model for chatbot | |
| CN110717012A (en) | Method, device, equipment and storage medium for recommending grammar | |
| CN110473524B (en) | Method and device for constructing voice recognition system | |
| US11783840B2 (en) | Video conference verbal junction identification via NLP | |
| CN114860910A (en) | Intelligent dialogue method and system | |
| US11776537B1 (en) | Natural language processing system for context-specific applier interface |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |