CN112732886A - Session management method, device, system and medium - Google Patents
Session management method, device, system and medium Download PDFInfo
- Publication number
- CN112732886A CN112732886A CN202110024091.2A CN202110024091A CN112732886A CN 112732886 A CN112732886 A CN 112732886A CN 202110024091 A CN202110024091 A CN 202110024091A CN 112732886 A CN112732886 A CN 112732886A
- Authority
- CN
- China
- Prior art keywords
- session
- keyword
- service group
- service
- keywords
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 45
- 238000012790 confirmation Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims description 39
- 238000004891 communication Methods 0.000 claims description 19
- 238000000034 method Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 description 6
- 238000002360 preparation method Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 1
- 235000017491 Bambusa tulda Nutrition 0.000 description 1
- 241001330002 Bambuseae Species 0.000 description 1
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 239000011425 bamboo Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to a session management method, a session management device, a session management system and a session management medium. The session management method comprises the following steps: acquiring session keywords in session information input by a user client in a session, and determining a service group to which each session keyword belongs; acquiring the session keyword weight of each session keyword in the data of the affiliated service group; when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to a preset threshold value, sending prompt information for switching to the manual session corresponding to any service group to the user client; and if receiving confirmation information of the user client responding to the prompt information, sending a control instruction to the user client to realize switching the current session to the manual session.
Description
Technical Field
The present invention relates to the field of intelligent interaction technologies, and in particular, to a session management method, apparatus, system, and medium.
Background
With the development of artificial intelligence technology, especially the rapid development of natural speech processing technology, man-machine conversation technology is more and more concerned and researched by people in all fields, and man-machine conversation products are also emerging continuously like bamboo shoots in spring after rain. In the technical field of customer service, a man-machine conversation system can provide related services such as consultation, sales and the like for customers continuously for 24 hours all the year round, and can greatly save manpower and cost expenditure, so that the intelligent customer service robot serving the customers is one of the man-machine conversation products with the highest commercial value and the largest use scene.
However, due to the limitation of the existing artificial intelligence technology, the existing intelligent customer service robot can provide services for customers all day at low cost, but cannot provide high-quality personalized services for the customers. In a traditional customer service system with 'robot response' intelligence, a manual button is generally hidden deeply, so that the cost of acquiring manual service by a customer under necessary conditions is increased, and the customer experience is poor; some problems needing background operation can be solved only by manual intervention, the traditional customer service system cannot actively change manual work, a user can pocket and change in an intelligent response link, a large amount of time is wasted, the problems cannot be solved, and the customer experience is poor; in an emergency scene, if customer account information is leaked, the user cannot conveniently acquire the manual service for the user, the user receives the robot response service for a long time, the customer processing time is delayed, and the user risk is increased.
In addition, the original mode of switching from user to manual mode is adopted, because the information carried by the manual switching request is limited, the customer must manually select the customer service group in the business field in which the customer problem cannot be known in the background manual switching service, the customer needs secondary switching because the customer cannot know the service and the like, and the customer may mistakenly enter the customer service group, so that the customer service and the consultation cost of the customer are increased; this problem is particularly acute in situations involving a wide range of service groups.
Disclosure of Invention
In order to solve the problems in the prior art, at least one embodiment of the present invention provides a session management method, device, system and storage medium.
In a first aspect, an embodiment of the present invention provides a session management method, where the session management method includes:
acquiring session keywords in session information input by a user client in a session, and determining a service group to which each session keyword belongs;
acquiring the session keyword weight of each session keyword in the data of the service group to which the session keyword belongs;
when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to a preset threshold value, sending prompt information for switching to the manual session corresponding to any service group to the user client;
and if receiving confirmation information of the user client responding to the prompt information, sending a control instruction to the user client to realize switching the current session to the manual session.
Based on the above technical solutions, the embodiments of the present invention may be further improved as follows.
With reference to the first aspect, in a first embodiment of the first aspect, the determining a service group to which each of the session keywords belongs includes:
comparing the session key words with the service key words in each service key word group respectively; each service group corresponds to a group of prestored service key phrases;
if the conversation keyword is matched with any business keyword, the conversation keyword belongs to a business group corresponding to the business keyword;
and if the session key words are not matched with all the service key words, the session key words do not belong to a service group.
With reference to the first embodiment of the first aspect, in a second embodiment of the first aspect, the obtaining a session keyword weight of the session keyword in the data of the attributed service group includes:
acquiring preset weight of each service keyword in the service group;
and taking the preset weight value of the service keyword matched with the session keyword as the session keyword weight of the session keyword.
With reference to the first aspect, in a third embodiment of the first aspect, the obtaining a session keyword weight of each session keyword in data of the attributed service group includes:
acquiring session data of the service group; wherein the session data comprises: a session information record and a session summary record;
acquiring word frequency and reverse file frequency of the conversation keywords in the conversation data;
and calculating the session keyword weight of the session keywords in the session data according to the word frequency and the reverse file frequency.
With reference to the first aspect, in a fourth embodiment of the first aspect, the sending, to the user client, a prompt message for switching to a manual session corresponding to any service group includes:
judging whether any service group is a service group for processing critical services;
if any service group is a service group for processing critical services, popping up the prompt message in a session window of the user client;
and if the any service group is not the service group for processing the critical service, popping up the prompt message in a preset area outside a session window of the user client.
With reference to the first aspect, in a fifth embodiment of the first aspect, the management method further includes:
when the accumulated value of the weights of the session keywords belonging to the session keywords in any service group is greater than or equal to a preset threshold value, judging whether the occurrence frequency of any session keyword in any service group is greater than or equal to a preset frequency;
and if the occurrence frequency of any session key word in any service group is greater than or equal to the preset frequency, switching the current session of the user client to the manual session corresponding to any service group.
With reference to the first aspect or the first, second, third, fourth, or fifth embodiment, in a sixth embodiment of the first aspect, the obtaining a session keyword in session information input by a user client in a session includes:
segmenting the conversation information to obtain a first prepared keyword;
respectively filtering stop words of the first prepared keywords to obtain second prepared keywords;
and performing synonym conversion on the second prepared keywords to obtain the conversation keywords.
In a second aspect, an embodiment of the present invention provides a session management apparatus, where the session management apparatus includes:
the first processing unit is used for acquiring session keywords in session information input by a user client in a session and determining a service group to which each session keyword belongs;
the second processing unit is used for acquiring the session keyword weight of each session keyword in the data of the affiliated service group;
the third processing unit is used for sending prompt information for switching to the manual session corresponding to any service group to the user client when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to a preset threshold value;
and the fourth processing unit is used for sending a control instruction to the user client side to realize switching the current session to the manual session if receiving confirmation information of the user client side responding to the prompt information.
In a third aspect, an embodiment of the present invention provides a session management system, including a processor, a communication interface, a memory, and a communication bus, where the processor and the communication interface complete communication between the memory and the processor through the communication bus;
a memory for storing a computer program;
a processor, configured to implement the session management method according to any embodiment of the first aspect when executing a program stored in a memory.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where one or more programs are stored, and the one or more programs are executable by one or more processors to implement the session management method described in any one of the first aspects.
Compared with the prior art, the technical scheme of the invention has the following advantages: the embodiment of the invention analyzes the session information input by the user, determines the session keywords in the session information and the service group to which each session keyword belongs, obtains the accumulated value of the weight values of the session keywords in each service group by combining the session keywords in the session information and the weight values corresponding to each session keyword, and actively provides a prompt for the user client to jump to the manual session when the accumulated value reaches a preset threshold value, namely, when the frequency of the session information input by the user in the session and related to the service of the service group reaches a certain value, provides the manual service of the corresponding service group for the user so as to facilitate the user to complete problem consultation, reduces the secondary switching rate by analyzing and matching the service groups, improves the customer experience, reduces the customer service cost and improves the session effectiveness.
Drawings
Fig. 1 is a schematic flowchart of a session management method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a session management method according to another embodiment of the present invention;
fig. 3 is a flowchart illustrating a session management method according to another embodiment of the present invention;
fig. 4 is a flowchart illustrating a session management method according to another embodiment of the present invention;
fig. 5 is a third schematic flowchart illustrating a session management method according to another embodiment of the present invention;
fig. 6 is a schematic structural diagram of a session management apparatus according to another embodiment of the present invention;
fig. 7 is a schematic structural diagram of a session management system according to yet another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a session management method. Referring to fig. 1, the method includes the steps of:
s11, obtaining the conversation key words in the conversation information input by the user client in the conversation, and determining the business group to which each conversation key word belongs.
In this embodiment, with the continuous development of business, a dedicated staff member is required to provide real-time consulting services for clients in all industries, and in order to reduce labor cost, and a man-machine conversation system can provide related services for clients without intermission, so man-machine conversation technology is receiving more and more attention and research from people in all fields.
In this embodiment, as the scale of an enterprise is enlarged, services that each enterprise can provide are more and more, and for the conversation robot, the problem that each client consults is uncertain, but different services have different characteristics and also have corresponding keywords, so that the service that the user wants to consult can be determined according to chat information input by the user, the service can be quickly provided for the user, the user experience using function is improved, and the condition that unwanted information is always provided for the user is avoided.
In this embodiment, session information input by a user in a session is obtained, keywords in the session information are extracted, and the keywords are respectively input into corresponding service groups, where it can be determined without any doubt that different service groups may have some overlapped service ranges, for example, a counter money drawing problem in a bank and a cash dispenser money drawing problem, the keywords are all money drawing, and in order to serve the user, the keywords may be respectively included in the counter service group and the cash dispenser service group, that is, one keyword may correspond to a plurality of service groups.
In this embodiment, associating the keywords with the service groups may determine the service group to which each keyword belongs through a preset keyword correspondence table, or train to obtain an identification model of each keyword and the service group based on the session information communicated in advance and the service finally selected by each session information, or calculate to obtain the importance of the keywords in the session information in any service group based on the session information communicated in advance and the service finally selected by each session information, and bind the keyword with any service group, of which the importance is greater than a preset threshold, so as to determine the service group to which the subsequent keyword belongs.
And S12, acquiring the session keyword weight of each session keyword in the data of the attributive service group.
In this embodiment, the session keyword weights of the session keywords are considered to be consistent according to the number of keywords in the service group to which the session keywords belong, and the session keyword weights of the service group are 1 divided by the number of the keywords, and the importance of the keywords in the session information in any service group can be calculated according to the finally selected service based on the previously communicated session information and each piece of session information provided in the above steps, and the importance of the keywords is used as the keyword weights; the word frequency of each conversation keyword can be counted based on the historical conversation information and the service business finally selected by each conversation information, the keyword weight of the keyword is determined according to the word frequency, and the higher the word frequency is, the larger the keyword weight is.
And S13, when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to a preset threshold value, sending prompt information for switching to the manual session corresponding to any service group to the user client.
In this embodiment, an accumulated value of the session keyword weights of the session keywords in each service group is counted, when a user has a man-machine conversation or has a manual conversation with another person, if the user continuously refers to a keyword of a certain service group, it is indicated that a service that the user wants to consult may be closer to the service group that the user has referred to, in this step, the service that the user wants to consult is determined by counting the accumulated value of the session keyword weights of the session keywords in the session information input by the user, and when the accumulated value reaches a preset threshold value, a prompt message indicating whether to switch to a manual session of the corresponding service group is sent to the user client, so as to avoid that the user cannot obtain a correct answer for a long time and cannot find a problem of poor experience caused by manual service, and improve the use experience of the user.
And S14, if the confirmation information of the user client responding to the prompt information is received, sending a control instruction to the user client to realize switching the current session to the manual session.
In this embodiment, when receiving the confirmation information of the user client responding to the prompt information, the user client is controlled to switch the current session to the corresponding manual session so as to complete the consultation service of the user; in this embodiment, when rejection information of a user client in response to a prompt message is received or no information is received for a long time, it is indicated that a manual session to be switched is not required by a user, or the user does not need to switch to the manual session, at this time, keywords in a service group corresponding to the manual session are cleared, a keyword weight value is also cleared, the session information sent by the user is continuously counted, session keywords are extracted, a new round of monitoring is performed, and when any user client ends the session, session keywords of all task groups and accumulated values of all calculation lists are cleared, so as to avoid interference on a next session.
In this embodiment, the session information input by the user is analyzed, the session keywords in the session information and the service groups to which each session keyword belongs are determined, the accumulated value of the weight values of the session keywords in each service group is obtained by combining the session keywords in the session information and the weight values corresponding to each session keyword, when the accumulated value reaches a preset threshold value, a prompt of jumping to a manual session is actively provided for the user client, that is, when the frequency of the session information input by the user in the session, which relates to the service of the service group, reaches a certain value, manual service of the corresponding service group is provided for the user, so that the user can complete problem consultation, the secondary switching rate is reduced by analyzing and matching the service groups, the customer experience is improved, the customer service cost is reduced, and the session effectiveness is improved.
In this embodiment, the obtaining of the session keyword in the session information input by the user client in the session includes: segmenting the conversation information to obtain a first prepared keyword; respectively filtering stop words of the first preparation keywords to obtain second preparation keywords; and performing synonym conversion on the second prepared keywords to obtain conversation keywords.
In this embodiment, the session information is subjected to word segmentation and stop word filtering to obtain a prepared keyword, a plurality of near-sense words are obtained by performing near-sense word conversion on the prepared keyword, and the prepared keyword and the converted near-sense words are used as the session keyword.
As shown in fig. 2, in this embodiment, the sending, to the user client, the prompt message for switching to the manual session corresponding to any service group in step S13 includes the following steps:
and S21, judging whether any service group is a service group for processing the critical service.
In this embodiment, the type of the service processed by the service group may be preset by the user, for example, the service group processing related to property, security, and the like should be a critical service, and other simpler services may be a common service group.
And S22a, if any service group is the service group for processing the critical service, popping up prompt information in the session window of the user client.
S22b, if any service group is not the service group for processing the critical service, popping up prompt information in a preset area outside a session window of the user client.
In this embodiment, a mode of popping up a prompt to the user client is controlled according to the service type of the service group, and the user can see the relevant information in time by popping up the prompt information in the session window, so that when the service type of the service group is a critical service, a more effective prompt mode is adopted to send a prompt to the user.
As shown in fig. 3, an embodiment of the present invention provides a session management method. Referring to fig. 3, the method includes the steps of:
s31, acquiring a session keyword in the session information input by the user client in the session;
regarding step S31, refer to the description in step S11 for details, which are not repeated herein.
S32, comparing the conversation key words with the service key words in each service key word group; each service group corresponds to a group of pre-stored service key phrases.
In this embodiment, the session keywords determined in the above steps are compared with the pre-stored service keywords to determine a service group to which the session keywords belong; specifically, for example, it may be directly determined whether the session keyword is consistent with the service keyword, if the session keyword is consistent with the service keyword, it is determined that the session keyword is matched with the service keyword, if the session keyword is inconsistent with the service keyword, the session keyword is not matched with the service keyword, or the session keyword is subjected to near-sense word conversion to obtain a plurality of near-sense words with similar meanings, the session keyword and the near-sense words are respectively compared with the service keyword, if the session keyword is consistent with the service keyword or the near-sense words are consistent with the service keyword, the session keyword is matched with the service keyword, otherwise, the session keyword is not matched with the service keyword.
And S33a, if the conversation keyword is matched with any business keyword, the conversation keyword belongs to the business group corresponding to the business keyword.
And S33b, if the conversation key words are not matched with all the service key words, the conversation key words do not belong to the service groups.
In this embodiment, a service group to which a session keyword belongs is determined according to whether the service keyword matched with the session keyword exists or not, if the service keyword matched with the session keyword does not exist, the session keyword can be deleted or disregarded, the session keyword not matched with any service keyword can be recorded, a user is prompted to process the session keyword, and the session keyword is entered into a service keyword group of a corresponding service group in a manual processing manner, so that the identification precision of session information of the user is improved.
And S34, acquiring the session keyword weight of each session keyword in the data of the attributive service group.
Regarding step S34, refer to the description in step S12 for details, which are not repeated herein.
And S35, when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to a preset threshold value, sending prompt information for switching to the manual session corresponding to any service group to the user client.
Regarding step S35, refer to the description in step S13 for details, which are not repeated herein.
And S36, if the confirmation information of the user client responding to the prompt information is received, sending a control instruction to the user client to realize switching the current session to the manual session.
Regarding step S36, refer to the description in step S14 for details, which are not repeated herein.
In this embodiment, by setting a service keyword group in advance corresponding to each service group, the service group to which the session keyword belongs in the session information input by the user is quickly determined according to the preset service keyword group, and the data processing efficiency is improved.
In this embodiment, obtaining the session keyword weight in the data of the attributed service group includes: acquiring preset weight of each service keyword in a service group; and taking the preset weight value of the service keyword matched with the session keyword as the session keyword weight of the session keyword.
In this embodiment, the preset value weight is set for each service keyword, where the setting manner of the weight may be set by the user, or the importance of each service keyword may be obtained as the preset weight by referring to the description in the above embodiments.
As shown in fig. 4, an embodiment of the present invention provides a session management method; referring to fig. 4, the session management method includes the steps of:
s41, obtaining the conversation key words in the conversation information input by the user client in the conversation, and determining the business group to which each conversation key word belongs.
Regarding step S41, refer to the description in step S11 for details, which are not repeated herein.
S42, acquiring session data of the service group; wherein the session data includes: session information records and session summary records.
In this embodiment, session data of a service group is obtained, that is, historical session data of the service group is obtained, and the weight of a session keyword in the service group is further determined according to a session information record and a session summary record in the session data.
And S43, acquiring the word frequency and the reverse file frequency of the conversation keywords in the conversation data.
In this embodiment, the occurrence frequency and the reverse file frequency of the session keyword in each type of session data are obtained, and a TF-IDF (term frequency-inverse document frequency) is a commonly used weighting technique for information retrieval and data mining, and a TFIDF is actually: TF, IDF, TF Term Frequency (Term Frequency), IDF Inverse file Frequency (Inverse Document Frequency). TF represents the frequency with which terms appear in document d. The main idea of IDF is: if the documents containing the entry t are fewer, that is, the smaller n is, the larger IDF is, the entry t has good category distinguishing capability. If the number of documents containing the entry t in a certain class of document C is m, and the total number of documents containing the entry t in other classes is k, it is obvious that the number of documents containing t is m + k, when m is large, n is also large, and the value of the IDF obtained according to the IDF formula is small, which means that the category distinguishing capability of the entry t is not strong. In practice, however, if a term frequently appears in a document of a class, it indicates that the term can well represent the characteristics of the text of the class, and such terms should be given higher weight and selected as characteristic words of the text of the class to distinguish the document from other classes.
And S44, calculating the weight of the session key words in the session data according to the word frequency and the reverse file frequency.
In this embodiment, the word frequency and the inverse file frequency are multiplied to obtain the session keyword weight of the session keyword.
And S45, when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to a preset threshold value, sending prompt information for switching to the manual session corresponding to any service group to the user client.
Regarding step S45, refer to the description in step S13 for details, which are not repeated herein.
And S46, if the confirmation information of the user client responding to the prompt information is received, sending a control instruction to the user client to realize switching the current session to the manual session.
Regarding step S46, refer to the description in step S14 for details, which are not repeated herein.
In this embodiment, the present scheme calculates the weights of the session keywords according to the word frequency and the reverse file frequency of the session keywords in the session data, and determines the service type that the user wants to consult according to the session information input by the user through the weight of each session keyword.
As shown in fig. 5, an embodiment of the present invention provides a session management method; referring to fig. 5, compared with the above-described embodiment, the difference is that the session management method includes the steps of:
s51, when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to a preset threshold value, judging whether the occurrence frequency of any session keyword in any service group is greater than or equal to a preset frequency.
And S52, if the occurrence frequency of any session key word in any service group is greater than or equal to the preset frequency, switching the current session of the user client to the manual session corresponding to any service group.
In the embodiment, the accumulated value of the session key weight of the session key in each service group is counted, when the user has a man-machine conversation or other manual conversations, if the user continuously mentions the keywords of a certain business group, it means that the service that the user wants to consult may be closer to the business group that the user directly mentions, in this step, the service that the user wants to consult is determined by counting the accumulated value of the session keyword weight of the session keywords in the session information input by the user, and when the accumulated value reaches a preset threshold value, judging whether the occurrence frequency of the session key words in any service group is greater than or equal to a preset frequency, if so, it indicates that the user is nervous about the problems he has presented, causing him to repeat the same problem all the time, at which point, the session can be directly switched to the manual session corresponding to the corresponding service group, so that the problem of the user can be solved in time.
As shown in fig. 6, an embodiment of the present invention provides a session management apparatus, including: a first processing unit 11, a second processing unit 12, a third processing unit 13 and a fourth processing unit 14.
In this embodiment, the first processing unit 11 is configured to obtain a session keyword in session information input by a user client in a session, and determine a service group to which each session keyword belongs;
in this embodiment, the second processing unit 12 is configured to obtain a session keyword weight of each session keyword in data of an attributed service group;
in this embodiment, the third processing unit 13 is configured to send, to the user client, a prompt message for switching to a manual session corresponding to any service group when an accumulated value of session keyword weights of session keywords belonging to any service group is greater than or equal to a preset threshold;
in this embodiment, the fourth processing unit 14 is configured to send a control instruction to the user client when receiving confirmation information that the user client responds to the prompt information, so as to implement switching the current session to the manual session.
In this embodiment, the first processing unit 11 is specifically configured to compare the session keyword with the service keyword in each service keyword group respectively; if the conversation keyword is matched with any business keyword, the conversation keyword belongs to a business group corresponding to the business keyword; if the session keywords are not matched with all the service keywords, the session keywords do not belong to a service group; each service group corresponds to a group of pre-stored service key phrases.
In this embodiment, the second processing unit 12 is specifically configured to obtain a preset weight of each service keyword in the service group; and taking the preset weight value of the service keyword matched with the session keyword as the session keyword weight of the session keyword.
In this embodiment, the second processing unit 12 is specifically configured to obtain session data of a service group; acquiring word frequency and reverse file frequency of session keywords in session data; calculating the conversation keyword weight of the conversation keyword in the conversation data according to the word frequency and the reverse file frequency; wherein the session data includes: session information records and session summary records.
In this embodiment, the third processing unit 13 is specifically configured to determine whether any service group is a service group that handles critical services; if any service group is a service group for processing the critical service, popping up prompt information in a session window of a user client; and if any service group is not the service group for processing the critical service, popping up prompt information in a preset area outside a session window of the user client.
In this embodiment, the management apparatus further includes: the fifth processing unit is used for judging whether the occurrence frequency of any session keyword in any service group is greater than or equal to the preset frequency or not when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to the preset threshold value; and if the occurrence frequency of any session key word in any service group is greater than or equal to the preset frequency, switching the current session of the user client to the manual session corresponding to any service group.
In this embodiment, the first processing unit 11 is specifically configured to perform word segmentation on the session information to obtain a first prepared keyword; respectively filtering stop words of the first preparation keywords to obtain second preparation keywords; and performing synonym conversion on the second prepared keywords to obtain conversation keywords.
As shown in fig. 7, an embodiment of the present invention provides a session management system, which includes a processor 1110, a communication interface 1120, a memory 1130, and a communication bus 1140, wherein the processor 1110, the communication interface 1120, and the memory 1130 complete communication with each other through the communication bus 1140;
a memory 1130 for storing computer programs;
acquiring session keywords in session information input by a user client in a session, and determining a service group to which each session keyword belongs;
acquiring the session keyword weight of each session keyword in the data of the affiliated service group;
when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to a preset threshold value, sending prompt information for switching to the manual session corresponding to any service group to the user client;
and if receiving confirmation information of the user client responding to the prompt information, sending a control instruction to the user client to realize switching the current session to the manual session.
In the electronic device provided in the embodiment of the present invention, the processor 1110 analyzes the session information input by the user by executing the program stored in the memory 1130, determines the session keywords in the session information and the service group to which each session keyword belongs, obtains an accumulated value of the weight values of the session keywords in each service group by combining the session keywords in the session information and the weight values corresponding to each session keyword, and actively provides a prompt for the user client to jump to the manual session when the accumulated value reaches a preset threshold value, so as to provide manual services of the corresponding service group for the user, so that the user can complete problem consultation.
The communication bus 1140 mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 1140 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface 1120 is used for communication between the electronic device and other devices.
The memory 1130 may include a Random Access Memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory 1130 may also be at least one memory device located remotely from the processor 1110.
The processor 1110 may be a general-purpose processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the integrated circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components.
Embodiments of the present invention provide a computer-readable storage medium, which stores one or more programs, where the one or more programs are executable by one or more processors to implement a session management method of any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions according to the embodiments of the invention are brought about in whole or in part when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (ssd)), among others.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A session management method, characterized in that the management method comprises:
acquiring session keywords in session information input by a user client in a session, and determining a service group to which each session keyword belongs;
acquiring the session keyword weight of each session keyword in the data of the service group to which the session keyword belongs;
when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to a preset threshold value, sending prompt information for switching to the manual session corresponding to any service group to the user client;
and if receiving confirmation information of the user client responding to the prompt information, sending a control instruction to the user client to realize switching the current session to the manual session.
2. The method according to claim 1, wherein the determining the service group to which each of the session keywords belongs comprises:
comparing the session key words with the service key words in each service key word group respectively; each service group corresponds to a group of prestored service key phrases;
if the conversation keyword is matched with any business keyword, the conversation keyword belongs to a business group corresponding to the business keyword;
and if the session key words are not matched with all the service key words, the session key words do not belong to a service group.
3. The method according to claim 2, wherein the obtaining the session keyword weight of the session keyword in the data of the attributed service group comprises:
acquiring preset weight of each service keyword in the service group;
and taking the preset weight value of the service keyword matched with the session keyword as the session keyword weight of the session keyword.
4. The method according to claim 1, wherein the obtaining the session keyword weight of each of the session keywords in the data of the belonging service group comprises:
acquiring session data of the service group; wherein the session data comprises: a session information record and a session summary record;
acquiring word frequency and reverse file frequency of the conversation keywords in the conversation data;
and calculating the session keyword weight of the session keywords in the session data according to the word frequency and the reverse file frequency.
5. The session management method according to claim 1, wherein the sending, to the user client, a prompt message for switching to a manual session corresponding to the service group includes:
judging whether any service group is a service group for processing critical services;
if any service group is a service group for processing critical services, popping up the prompt message in a session window of the user client;
and if the any service group is not the service group for processing the critical service, popping up the prompt message in a preset area outside a session window of the user client.
6. The session management method according to claim 1, wherein the management method further comprises:
when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to a preset threshold value, judging whether the occurrence frequency of any session keyword in any service group is greater than or equal to a preset frequency;
and if the occurrence frequency of any session key word in any service group is greater than or equal to the preset frequency, switching the current session of the user client to the manual session corresponding to any service group.
7. The session management method according to any one of claims 1 to 6, wherein the acquiring the session key words in the session information input by the user client in the session comprises:
segmenting the conversation information to obtain a first prepared keyword;
respectively filtering stop words of the first prepared keywords to obtain second prepared keywords;
and performing synonym conversion on the second prepared keywords to obtain the conversation keywords.
8. A session management apparatus, characterized in that the session management apparatus comprises:
the first processing unit is used for acquiring session keywords in session information input by a user client in a session and determining a service group to which each session keyword belongs;
the second processing unit is used for acquiring the session keyword weight of each session keyword in the data of the affiliated service group;
the third processing unit is used for sending prompt information for switching to the manual session corresponding to any service group to the user client when the accumulated value of the session keyword weights of the session keywords belonging to any service group is greater than or equal to a preset threshold value;
and the fourth processing unit is used for sending a control instruction to the user client side to realize switching the current session to the manual session if receiving confirmation information of the user client side responding to the prompt information.
9. The session management system is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing the communication between the processor and the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the session management method according to any one of claims 1 to 7 when executing a program stored in a memory.
10. A computer-readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the session management method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110024091.2A CN112732886A (en) | 2021-01-08 | 2021-01-08 | Session management method, device, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110024091.2A CN112732886A (en) | 2021-01-08 | 2021-01-08 | Session management method, device, system and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112732886A true CN112732886A (en) | 2021-04-30 |
Family
ID=75589735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110024091.2A Pending CN112732886A (en) | 2021-01-08 | 2021-01-08 | Session management method, device, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112732886A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | ***通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN105701088A (en) * | 2016-02-26 | 2016-06-22 | 北京京东尚科信息技术有限公司 | Method and device for switching machine conversation to artificial conversation |
| KR20180013820A (en) * | 2017-08-07 | 2018-02-07 | (주)씨제이텔레닉스 | System and method for analyzing customer type using speech analysis |
| CN108121821A (en) * | 2018-01-09 | 2018-06-05 | 惠龙易通国际物流股份有限公司 | A kind of machine customer service method, equipment and computer storage media |
| CN108228837A (en) * | 2018-01-04 | 2018-06-29 | 北京百悟科技有限公司 | Customer mining processing method and processing device |
| CN108920579A (en) * | 2018-06-22 | 2018-11-30 | 龙马智芯（珠海横琴）科技有限公司 | Classification method, device, terminal device and the storage medium of sentence |
| CN110377712A (en) * | 2019-07-12 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of intelligence conversation switching method, device, equipment and storage medium |
| WO2019218527A1 (en) * | 2018-05-14 | 2019-11-21 | 平安科技（深圳）有限公司 | Multi-system combined natural language processing method and apparatus |
| CN112182188A (en) * | 2020-09-30 | 2021-01-05 | 珠海格力电器股份有限公司 | Knowledge graph-based question and answer method and device and storage medium |
-
2021
- 2021-01-08 CN CN202110024091.2A patent/CN112732886A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | ***通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN105701088A (en) * | 2016-02-26 | 2016-06-22 | 北京京东尚科信息技术有限公司 | Method and device for switching machine conversation to artificial conversation |
| KR20180013820A (en) * | 2017-08-07 | 2018-02-07 | (주)씨제이텔레닉스 | System and method for analyzing customer type using speech analysis |
| CN108228837A (en) * | 2018-01-04 | 2018-06-29 | 北京百悟科技有限公司 | Customer mining processing method and processing device |
| CN108121821A (en) * | 2018-01-09 | 2018-06-05 | 惠龙易通国际物流股份有限公司 | A kind of machine customer service method, equipment and computer storage media |
| WO2019218527A1 (en) * | 2018-05-14 | 2019-11-21 | 平安科技（深圳）有限公司 | Multi-system combined natural language processing method and apparatus |
| CN108920579A (en) * | 2018-06-22 | 2018-11-30 | 龙马智芯（珠海横琴）科技有限公司 | Classification method, device, terminal device and the storage medium of sentence |
| CN110377712A (en) * | 2019-07-12 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of intelligence conversation switching method, device, equipment and storage medium |
| CN112182188A (en) * | 2020-09-30 | 2021-01-05 | 珠海格力电器股份有限公司 | Knowledge graph-based question and answer method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11645321B2 (en) | Calculating relationship strength using an activity-based distributed graph | |
| US11004013B2 (en) | Training of chatbots from corpus of human-to-human chats | |
| US10536579B2 (en) | System, method and marketplace for real-time interactive video/voice services using artificial intelligence | |
| US20210224832A1 (en) | Method and apparatus for predicting customer purchase intention, electronic device and medium | |
| US20210365963A1 (en) | Target customer identification method and device, electronic device and medium | |
| KR101719196B1 (en) | Apparatus for forecasting purpose of customer counsel and computer-readable medium thereof | |
| CN112507116B (en) | Customer portrait method based on customer response corpus and related equipment thereof | |
| CN111461180B (en) | Sample classification method, device, computer equipment and storage medium | |
| WO2018045915A1 (en) | Method and apparatus for adjusting service voice playback sequence | |
| EP2382761A1 (en) | Predictive engine for interactive voice response system | |
| KR101645992B1 (en) | Apparatus for monitering customer complaint and computer-readable medium thereof | |
| JP3872689B2 (en) | Security policy creation support system and security measure decision support system | |
| CN113313279A (en) | Document auditing method and device | |
| CN111191046A (en) | Method, device, computer storage medium and terminal for realizing information search | |
| US20210065204A1 (en) | Analyzing method, analyzing device, and computer-readable recording medium | |
| CN105745679B (en) | System and method for discovering and exploring concepts | |
| JP6752330B1 (en) | Machine learning-based matching equipment and matching methods | |
| US11250365B2 (en) | Systems and methods for utilizing compliance drivers to conserve system resources and reduce compliance violations | |
| US10924611B2 (en) | Voice recognition system and call evaluation setting method | |
| CN115170153B (en) | Work order processing method and device based on multidimensional attribute and storage medium | |
| CN112732886A (en) | Session management method, device, system and medium | |
| CN110930238A (en) | Method, device, equipment and computer readable medium for improving audit task efficiency | |
| CN116433324A (en) | Product recommendation method, device, medium and computer equipment | |
| US20150200903A1 (en) | Automatic email address input process | |
| US20220172257A1 (en) | System and method for sales forecasting and optimal path to opportunity closure using signals from mailbox activity and conversational data |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 221, 2 / F, block C, 18 Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant after: Jingdong Technology Holding Co.,Ltd. Address before: Room 221, 2 / F, block C, 18 Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant before: Jingdong Digital Technology Holding Co., Ltd |