CN111222043A - Information processing method and system and electronic equipment - Google Patents
Information processing method and system and electronic equipment Download PDFInfo
- Publication number
- CN111222043A CN111222043A CN201911425098.4A CN201911425098A CN111222043A CN 111222043 A CN111222043 A CN 111222043A CN 201911425098 A CN201911425098 A CN 201911425098A CN 111222043 A CN111222043 A CN 111222043A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- record
- record information
- condition
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
Abstract
The application discloses an information processing method, an information processing system and electronic equipment, wherein after input information of a user is acquired, the intention of the user is confirmed, a record with the similarity meeting a condition with the intention of the user is searched from a historical record, and the searched record is output.
Description
Technical Field
The present application relates to the field of control, and in particular, to an information processing method and system, and an electronic device.
Background
In the process of communicating the intelligent customer service system with the user, the user puts forward a question, and the intelligent customer service system identifies the question of the user and outputs a standard question for the user to select. However, the standard questions are generally short and ambiguous, and the user cannot understand the standard questions output by the system, thereby resulting in poor communication.
Disclosure of Invention
In view of the above, the present application provides an information processing method, system and electronic device, and the specific scheme is as follows:
an information processing method comprising:
acquiring input information of a user;
identifying the input information to determine a user intent;
searching record information with the similarity meeting a first condition with the user intention from a historical record as first record information, and outputting the first record information to enable the user to determine whether the first record information is matched with the input information;
wherein the history is input information of a plurality of users stored in advance.
Further, the method also comprises the following steps:
and determining whether the user intention meets a second condition, and if the user intention meets the second condition, searching the record information with the similarity meeting the first condition with the user intention from the history record as first record information.
Further, the method also comprises the following steps:
identifying the input information to determine the expression type of the user;
the searching for record information with similarity to the user intention meeting a first condition from a history record as first record information and outputting the first record information includes:
and searching the historical record for record information meeting the condition of similarity with the user intention and the expression type of the user as first record information, and outputting the first record information.
Further, the searching, from the history, for record information whose similarity to the user intention and the expression type of the user satisfies a condition as first record information, and outputting the first record information includes:
searching record information meeting a third condition with the expression type of the user from a historical record as second record information;
and searching the second recording information for recording information with the similarity meeting a first condition with the user intention as first recording information, and outputting the first recording information.
Further, the searching, from the history, for record information whose similarity to the user intention and the expression type of the user satisfies a condition as first record information, and outputting the first record information includes:
searching record information with the similarity meeting a first condition with the user intention from a historical record as third record information;
and searching the third record information for record information meeting a third condition with the expression type of the user as first record information, and outputting the first record information.
Further, the searching, from the history, for record information whose similarity to the user intention satisfies a first condition as first record information, and outputting the first record information includes:
searching record information with the similarity meeting a first condition with the user intention from a historical record;
and if the number of the record information with the similarity meeting the first condition is not less than 2, performing priority arrangement on the not less than 2 record information according to the similarity, taking the arranged not less than 2 record information as first record information, and outputting the first record information.
Further, the method also comprises the following steps:
determining standard information which is stored in advance and has the similarity with the user intention and meets a fourth condition;
the outputting the first recording information includes:
and outputting the standard information and the first recorded information as an output result so that a user can confirm whether the first recorded information is matched with the input information and confirm whether the standard information is matched with the input information.
An information processing system comprising:
an acquisition unit configured to acquire input information of a user;
an identification unit for identifying the input information to determine a user intention;
an output unit configured to search a history for a record whose similarity to the user intention satisfies a first condition as first record information, and output the first record information so that the user determines whether the first record information matches the input information;
wherein the history is input information of a plurality of users stored in advance.
Further, the method also comprises the following steps:
and the determining unit is used for determining whether the user intention meets a second condition, and if the user intention meets the second condition, searching the record information with the similarity meeting the first condition with the user intention from the history record as first record information.
An electronic device, comprising:
the processor is used for acquiring input information of a user, identifying the input information to determine user intention, searching record information with similarity meeting a first condition with the user intention from a historical record to serve as first record information, and outputting the first record information to enable the user to determine whether the first record information is matched with the input information;
and the memory is used for storing the history records, and the history records are pre-stored input information of a plurality of users.
According to the technical scheme, the information processing method, the information processing system and the electronic device, input information of a user is obtained, the input information is identified to determine the intention of the user, record information with the similarity meeting a first condition with the intention of the user is searched from a historical record to serve as first record information, and the first record information is output to enable the user to determine whether the first record information is matched with the input information or not, wherein the historical record is pre-stored input information of a plurality of users. According to the scheme, after the input information of the user is acquired, the intention of the user is confirmed, the record meeting the condition of the similarity with the intention of the user is searched from the historical record, and the searched record is output, the record information meeting the first condition of the similarity with the intention of the user is output, the record information is the input information meeting the input habit of the user, and the user can more accurately and definitely determine whether the input information meeting the input habit of the user is matched with the input information of the user instead of directly outputting the standard problem, so that the problem of poor communication caused by the fact that the user cannot understand the standard problem is solved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an information processing method disclosed in an embodiment of the present application;
fig. 2 is a flowchart of an information processing method disclosed in an embodiment of the present application;
FIG. 3 is a flow chart of an information processing method disclosed in an embodiment of the present application;
FIG. 4 is a block diagram of an information handling system according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The application discloses an information processing method, a flow chart of which is shown in fig. 1, comprising the following steps:
step S11, acquiring input information of a user;
step S12, recognizing the input information to determine the user intention;
and step 13, searching the history record as the first record information, wherein the similarity of the first record information and the user intention meets the first condition, and outputting the first record information to enable the user to determine whether the first record information is matched with the input information, wherein the history record is the input information of a plurality of users stored in advance.
In the communication process of the intelligent customer service system and the user, if the user has input information, the intelligent customer service system receives the input information of the user, usually directly identifies the input information and outputs standard problems, namely the problem that the input information of the user is matched after the input information is identified by the intelligent customer service system, but the standard problems are short and small, ambiguity is easily caused, and the user cannot determine whether the standard problems are matched with the input information of the user, so that repeated input of the user can be caused, the intelligent customer service system can repeatedly output the standard problems, and the use experience of the user is greatly reduced.
In order to solve the problem, the scheme identifies the input information of the user after acquiring the input information, so as to determine the intention of the user.
Specifically, the user intent is to identify the user's input information to determine what the user wants to do, such as: keyword recognition, semantic recognition, etc. are performed on the input information, thereby determining the user's intention.
And storing the historical records so as to search the matched records from the historical records for output after the user intention is determined.
Specifically, the history is the input information of a plurality of users stored in advance, that is, the input information of a plurality of users that the intelligent customer service system has successfully identified in the history, so as to learn the language habits or expression habits of the plurality of users.
And searching the record information with the similarity meeting the first condition with the user intention from the historical record as first record information, and outputting the first record information to enable the user to determine whether the first record information is matched with the input information.
And arranging the record information in the history records according to the similarity with the user intention, and determining the record meeting the first condition from the record information and outputting the record. Satisfying the first condition may be: if the similarity between the record information in the history record and the user intention is higher than a certain preset value, determining that the record information in the history record meets a first condition; or after the record information in the history records is arranged according to the similarity with the intention of the user, the preset number of record information in the history records with the similarity value larger than that of other record information is determined to be output as the first record information, namely the record information in each history record with the first preset number is arranged according to the similarity value from high to low and is output as the first record information.
Further, the method also comprises the following steps: searching for the record information with the similarity meeting the first condition with the user intention from the historical record, if the number of the record information with the similarity meeting the first condition is not less than 2, carrying out priority arrangement on the not less than 2 record information according to the similarity value, and outputting the arranged not less than 2 record information as the first record information.
The method comprises the steps of screening output information according to the similarity, when a plurality of pieces of record information screened out from a history record meet a first condition, rearranging the plurality of pieces of record information screened out according to the height of the similarity value, and outputting the plurality of pieces of record information according to the rearranged sequence, so that the record information which is output by an intelligent customer service system and is arranged according to the similarity with the user intention from high to low is output by a user, namely the closer to the front, the higher the similarity is, the more likely the first record information is to be matched with the user intention, the user is prevented from seeing the first record information which is not arranged according to the height of the similarity value, the user is not convenient to search, and the user experience is reduced.
In addition, the following may be also possible:
after the output information is screened according to the similarity, when the plurality of record information in the screened history records all meet the first condition, the screened plurality of record information is rearranged, at the moment, the rearrangement is not arranged according to the sequence of the similarity with the intention of the user, but is arranged according to the number of the same words in the input information of the user, the plurality of record information meeting the first condition in the screened history records are compared again, which record information is the most number of the same words in the input information of the user is determined, and then the arranged plurality of record information is arranged according to the number of the same words, and the arranged plurality of record information is output.
After the first record information is output, the user selects a record matched with the input information input by the user from the output first record information as a re-input, and the re-input result of the user, namely the feedback result of the user input information identification received by the intelligent customer service system.
If the user selects one of the first records for inputting again, the input information of the user can be matched with the record selected from the first records, and the input information is stored in the history record to be used as a success case; if the user makes another input in the dialog box, it can be clear that there is no record information matching with the user's intention in the first record information, and the input information of the user and the first record information can be stored together as a negative sample, i.e. a failure case, and not stored in the history of the success case.
The information processing method disclosed in this embodiment acquires input information of a user, identifies the input information to determine user intention, searches, as first record information, record information whose similarity to the user intention satisfies a first condition from a history, and outputs the first record information to enable the user to determine whether the first record information matches the input information, where the history is input information of a plurality of users stored in advance. According to the scheme, after the input information of the user is acquired, the intention of the user is confirmed, the record meeting the condition of the similarity with the intention of the user is searched from the historical record, and the searched record is output, the record information meeting the first condition of the similarity with the intention of the user is output, the record information is the input information meeting the input habit of the user, and the user can more accurately and definitely determine whether the input information meeting the input habit of the user is matched with the input information of the user instead of directly outputting the standard problem, so that the problem of poor communication caused by the fact that the user cannot understand the standard problem is solved.
The present embodiment discloses an information processing method, a flowchart of which is shown in fig. 2, and includes:
step S21, acquiring input information of a user;
step S22, recognizing the input information to determine the user intention;
and step S23, determining whether the user intention meets a second condition, if so, searching the record information with the similarity meeting the first condition with the user intention from the history record as the first record information and outputting the first record information so that the user can determine whether the first record information is matched with the input information, wherein the history record is the pre-stored input information of a plurality of users.
After the input information of the user is identified and the user intention is determined, whether the user intention meets a second condition is determined, and only when the user intention meets the second condition, the record information with the similarity degree meeting the first condition with the user intention is searched from the historical record.
Whether the user intention satisfies the second condition may be: after semantic recognition is carried out on input information of a user, the fact that the input information of the user lacks necessary elements is determined, at the moment, the intention of the user can be determined, the intention of the user is output, so that the user can determine whether the intention of the user is matched with the real intention of the user, if the intention of the user is matched with the real intention of the user, the step of searching record information with the similarity meeting a first condition from a historical record is carried out continuously, and if the intention of the user is not matched with the real intention of the user, feedback information lacking the necessary elements is output, so that the user supplements the necessary elements according to the feedback information, and the intention can be matched;
in addition, after determining that the input information of the user lacks necessary elements, feedback information lacking the necessary elements may be directly output without continuing the determination of the user's intention, so that the user supplements the necessary elements based on the feedback information, thereby enabling the intention to be matched with the input information. Specifically, after determining that the user supplements complete necessary elements according to the feedback information, the user intention is determined, and then record information with similarity to the user intention meeting a first condition is searched from a historical record.
Whether the user intention satisfies the second condition may be: identifying input information of a user, determining whether the accuracy of the user intention reaches a certain numerical value after determining the user intention, and continuing to perform the subsequent step of searching the record information of which the similarity with the user intention meets a first condition from the historical record only when the accuracy reaches the certain numerical value; and if the accuracy does not reach a certain numerical value, continuing to determine the user intention in other ways until the determined accuracy of the user intention reaches the certain numerical value.
Determining whether the accuracy of the user's intent reaches a certain value may be: and when the current identification mode is adopted for input information identification in history identification, determining whether the accuracy of the current identification mode reaches a certain value, namely determining the accuracy of the current identification mode from record identification, and if the accuracy of the current identification mode does not meet the condition, adopting other identification modes for identification.
The information processing method disclosed in this embodiment acquires input information of a user, identifies the input information to determine user intention, searches, as first record information, record information whose similarity to the user intention satisfies a first condition from a history, and outputs the first record information to enable the user to determine whether the first record information matches the input information, where the history is input information of a plurality of users stored in advance. According to the scheme, after the input information of the user is acquired, the intention of the user is confirmed, the record meeting the condition of the similarity with the intention of the user is searched from the historical record, and the searched record is output, the record information meeting the first condition of the similarity with the intention of the user is output, the record information is the input information meeting the input habit of the user, and the user can more accurately and definitely determine whether the input information meeting the input habit of the user is matched with the input information of the user instead of directly outputting the standard problem, so that the problem of poor communication caused by the fact that the user cannot understand the standard problem is solved.
The present embodiment discloses an information processing method, a flowchart of which is shown in fig. 3, and the method includes:
step S31, acquiring input information of a user;
step S32, identifying the input information, and determining the user intention and the expression type of the user;
step S33, searching the history for the record information satisfying the condition of similarity with the user 'S intention and the user' S expression type as the first record information, and outputting the first record information to enable the user to determine whether the first record information matches with the input information.
When the user intention is determined, the expression type of the user also needs to be determined, namely, not only the user intention but also the language habit of the user needs to be determined, such as: expressions, word habits, and the like.
The history records are recorded with input information of a plurality of users, and are cases of successfully recognizing the user intention in the history recognition records, such as: the input information of the user is: my phone cannot turn on the flash while video, and the first record information is: what do you get back is that the flash light is not available when the video is. In this example, the same intention is expressed regardless of the input information of the user or the first recorded information, and the first recorded information is also input information of other users in the history.
The input information of a plurality of users is stored in the history record, so the intentions of the plurality of users and the expression types of the plurality of users are stored, different users have the same or different expression modes, and when the feedback is carried out by adopting the expression mode the same as the input information of the users, the user identity is easier to improve, and the use experience of the users is improved.
Specifically, the record information satisfying the third condition with the expression type of the user is searched from the history as the second record information, the record information satisfying the first condition with the similarity to the user intention is searched from the second record information as the first record information, and the first record information is output.
Firstly, searching through an expression type, taking all records in the history record, which are the same as the expression type of the user, as second record information, wherein the second record information comprises records which are the same as the intention of the user and records which are different from the user records; and then searching the record of which the similarity with the user intention meets the first condition from the second record information, namely searching the similarity of the user intention on the premise of firstly ensuring that the expression types are the same, thereby ensuring that the output first record information can ensure that the user intentions are similar and the expression types are the same.
In addition, the following may be also possible: and searching a record with the similarity meeting the first condition with the intention of the user from the historical record as third record information, searching the record information meeting the third condition with the expression type of the user from the third record information as the first record information, and outputting the first record information.
That is, the user intention may be searched for first, and a record in the history record, the similarity of which to the user intention satisfies the first condition, is used as third record information, where the third record information includes both a record of the same expression type as the user and a record of a different expression type from the user; and then searching for the record with the same expression type as the user from the third record information, namely ensuring that the user intention is the same firstly and then embracing the expression type to be the same.
Of course, the user intention and the expression habit may be searched at the same time, and the final first recorded information may be directly obtained and output.
In addition, when searching for the record information of the same expression type as the user, the following specific steps may be performed: and searching the recorded information which is the same as or similar to the expression type of the user, namely, only one expression type which is in accordance with the user can be found in the word habit and the expression mode.
Further, the method also comprises the following steps: determining standard information which is stored in advance and has similarity with the user intention and meets a fourth condition; outputting first recording information including: and outputting the standard information and the first recorded information as an output result so that the user can confirm whether the first recorded information is matched with the input information and confirm whether the standard information is matched with the input information.
If the user inputs information, the intelligent customer service system identifies and outputs only the first recorded information as an output result, the user only sees the first recorded information, that is, only outputs a final determination result, but does not output the user intention determined in the process, which may cause that, if the first recorded information does not contain information matched with the input information, the user may continue to input information, at this time, the intelligent customer service system does not know whether the identified user intention is incorrect, whether the finally output first recorded information is different from the expression type of the input information, or whether the finally output first recorded information is not highly similar to the input information.
Therefore, the standard information is output while the first recorded information is output, so that a user can determine which link is identified by error, and the intelligent customer service system can know which link to perform correction again.
The standard information is pre-stored, the similarity between the output standard information and the user intention meets a fourth condition, namely the standard information and the user intention can be equivalent, if the user determines that the standard information output by the intelligent customer service system is correct and the first record information is incorrect, the user intention can be determined to be correct in identification, and then only the record with the similarity between the output standard information and the user intention meeting the first condition needs to be searched continuously from the history record;
if the user determines that the standard information output by the intelligent customer service system is wrong, the first recorded information is also necessary to be wrong, at this moment, the problem that the user intention is identified can be determined, the intelligent customer service system needs to re-identify the input information of the user, re-confirm the user intention, and on the basis, re-search the first recorded information from the historical record until the output first recorded information and the standard information are both correct, the intelligent customer service system can be determined to be completely correct, and at this moment, a solution can be fed back to the user based on the input information of the user only to be correct.
The information processing method disclosed in this embodiment acquires input information of a user, identifies the input information to determine user intention, searches, as first record information, record information whose similarity to the user intention satisfies a first condition from a history, and outputs the first record information to enable the user to determine whether the first record information matches the input information, where the history is input information of a plurality of users stored in advance. According to the scheme, after the input information of the user is acquired, the intention of the user is confirmed, the record meeting the condition of the similarity with the intention of the user is searched from the historical record, and the searched record is output, the record information meeting the first condition of the similarity with the intention of the user is output, the record information is the input information meeting the input habit of the user, and the user can more accurately and definitely determine whether the input information meeting the input habit of the user is matched with the input information of the user instead of directly outputting the standard problem, so that the problem of poor communication caused by the fact that the user cannot understand the standard problem is solved.
The present embodiment discloses an information processing system, a schematic structural diagram of which is shown in fig. 4, and the information processing system includes:
The acquiring unit 41 is used for acquiring input information of a user;
the recognition unit 42 is used for recognizing the input information to determine the user intention;
the output unit 43 is configured to search, from the history, a record whose similarity to the user's intention satisfies a first condition as first record information, and output the first record information so that the user determines whether the first record information matches the input information;
the history records are pre-stored input information of a plurality of users.
In the communication process of the intelligent customer service system and the user, if the user has input information, the intelligent customer service system receives the input information of the user, usually directly identifies the input information and outputs standard problems, namely the problem that the input information of the user is matched after the input information is identified by the intelligent customer service system, but the standard problems are short and small, ambiguity is easily caused, and the user cannot determine whether the standard problems are matched with the input information of the user, so that repeated input of the user can be caused, the intelligent customer service system can repeatedly output the standard problems, and the use experience of the user is greatly reduced.
In order to solve the problem, the scheme identifies the input information of the user after acquiring the input information, so as to determine the intention of the user.
Specifically, the user intent is to identify the user's input information to determine what the user wants to do, such as: keyword recognition, semantic recognition, etc. are performed on the input information, thereby determining the user's intention.
And storing the historical records so as to search the matched records from the historical records for output after the user intention is determined.
Specifically, the history is the input information of a plurality of users stored in advance, that is, the input information of a plurality of users that the intelligent customer service system has successfully identified in the history, so as to learn the language habits or expression habits of the plurality of users.
And searching the record information with the similarity meeting the first condition with the user intention from the historical record as first record information, and outputting the first record information to enable the user to determine whether the first record information is matched with the input information.
And arranging the record information in the history records according to the similarity with the user intention, and determining the record meeting the first condition from the record information and outputting the record. Satisfying the first condition may be: if the similarity between the record information in the history record and the user intention is higher than a certain preset value, determining that the record information in the history record meets a first condition; or after the record information in the history records is arranged according to the similarity with the intention of the user, the preset number of record information in the history records with the similarity value larger than that of other record information is determined to be output as the first record information, namely the record information in each history record with the first preset number is arranged according to the similarity value from high to low and is output as the first record information.
Further, the method also comprises the following steps: searching for the record information with the similarity meeting the first condition with the user intention from the historical record, if the number of the record information with the similarity meeting the first condition is not less than 2, carrying out priority arrangement on the not less than 2 record information according to the similarity value, and outputting the arranged not less than 2 record information as the first record information.
The method comprises the steps of screening output information according to the similarity, when a plurality of pieces of record information screened out from a history record meet a first condition, rearranging the plurality of pieces of record information screened out according to the height of the similarity value, and outputting the plurality of pieces of record information according to the rearranged sequence, so that the record information which is output by an intelligent customer service system and is arranged according to the similarity with the user intention from high to low is output by a user, namely the closer to the front, the higher the similarity is, the more likely the first record information is to be matched with the user intention, the user is prevented from seeing the first record information which is not arranged according to the height of the similarity value, the user is not convenient to search, and the user experience is reduced.
In addition, the following may be also possible:
after the output information is screened according to the similarity, when the plurality of record information in the screened history records all meet the first condition, the screened plurality of record information is rearranged, at the moment, the rearrangement is not arranged according to the sequence of the similarity with the intention of the user, but is arranged according to the number of the same words in the input information of the user, the plurality of record information meeting the first condition in the screened history records are compared again, which record information is the most number of the same words in the input information of the user is determined, and then the arranged plurality of record information is arranged according to the number of the same words, and the arranged plurality of record information is output.
After the first record information is output, the user selects a record matched with the input information input by the user from the output first record information as a re-input, and the re-input result of the user, namely the feedback result of the user input information identification received by the intelligent customer service system.
If the user selects one of the first records for inputting again, the input information of the user can be matched with the record selected from the first records, and the input information is stored in the history record to be used as a success case; if the user makes another input in the dialog box, it can be clear that there is no record information matching with the user's intention in the first record information, and the input information of the user and the first record information can be stored together as a negative sample, i.e. a failure case, and not stored in the history of the success case.
Further, the information processing system disclosed in this embodiment may further include: a determination unit.
The determining unit is used for determining whether the user intention meets a second condition, and if the user intention meets the second condition, searching the record information with the similarity meeting the first condition with the user intention from the history record as first record information.
After the input information of the user is identified and the user intention is determined, whether the user intention meets a second condition is determined, and only when the user intention meets the second condition, the record information with the similarity degree meeting the first condition with the user intention is searched from the historical record.
Whether the user intention satisfies the second condition may be: after semantic recognition is carried out on input information of a user, the fact that the input information of the user lacks necessary elements is determined, at the moment, the intention of the user can be determined, the intention of the user is output, so that the user can determine whether the intention of the user is matched with the real intention of the user, if the intention of the user is matched with the real intention of the user, the step of searching record information with the similarity meeting a first condition from a historical record is carried out continuously, and if the intention of the user is not matched with the real intention of the user, feedback information lacking the necessary elements is output, so that the user supplements the necessary elements according to the feedback information, and the intention can be matched;
in addition, after determining that the input information of the user lacks necessary elements, feedback information lacking the necessary elements may be directly output without continuing the determination of the user's intention, so that the user supplements the necessary elements based on the feedback information, thereby enabling the intention to be matched with the input information. Specifically, after determining that the user supplements complete necessary elements according to the feedback information, the user intention is determined, and then record information with similarity to the user intention meeting a first condition is searched from a historical record.
Whether the user intention satisfies the second condition may be: identifying input information of a user, determining whether the accuracy of the user intention reaches a certain numerical value after determining the user intention, and continuing to perform the subsequent step of searching the record information of which the similarity with the user intention meets a first condition from the historical record only when the accuracy reaches the certain numerical value; and if the accuracy does not reach a certain numerical value, continuing to determine the user intention in other ways until the determined accuracy of the user intention reaches the certain numerical value.
Determining whether the accuracy of the user's intent reaches a certain value may be: and when the current identification mode is adopted for input information identification in history identification, determining whether the accuracy of the current identification mode reaches a certain value, namely determining the accuracy of the current identification mode from record identification, and if the accuracy of the current identification mode does not meet the condition, adopting other identification modes for identification.
Further, the identification unit identifies the input information, determines the intention of the user, and can also determine the expression type of the user.
And searching the record information with the similarity meeting the conditions with the user intention and the expression type of the user from the historical record to serve as first record information, and outputting the first record information.
When the user intention is determined, the expression type of the user also needs to be determined, namely, not only the user intention but also the language habit of the user needs to be determined, such as: expressions, word habits, and the like.
The history records are recorded with input information of a plurality of users, and are cases of successfully recognizing the user intention in the history recognition records, such as: the input information of the user is: my phone cannot turn on the flash while video, and the first record information is: what do you get back is that the flash light is not available when the video is. In this example, the same intention is expressed regardless of the input information of the user or the first recorded information, and the first recorded information is also input information of other users in the history.
The input information of a plurality of users is stored in the history record, so the intentions of the plurality of users and the expression types of the plurality of users are stored, different users have the same or different expression modes, and when the feedback is carried out by adopting the expression mode the same as the input information of the users, the user identity is easier to improve, and the use experience of the users is improved.
Specifically, the record information satisfying the third condition with the expression type of the user is searched from the history as the second record information, the record information satisfying the first condition with the similarity to the user intention is searched from the second record information as the first record information, and the first record information is output.
Firstly, searching through an expression type, taking all records in the history record, which are the same as the expression type of the user, as second record information, wherein the second record information comprises records which are the same as the intention of the user and records which are different from the user records; and then searching the record of which the similarity with the user intention meets the first condition from the second record information, namely searching the similarity of the user intention on the premise of firstly ensuring that the expression types are the same, thereby ensuring that the output first record information can ensure that the user intentions are similar and the expression types are the same.
In addition, the following may be also possible: and searching a record with the similarity meeting the first condition with the intention of the user from the historical record as third record information, searching the record information meeting the third condition with the expression type of the user from the third record information as the first record information, and outputting the first record information.
That is, the user intention may be searched for first, and a record in the history record, the similarity of which to the user intention satisfies the first condition, is used as third record information, where the third record information includes both a record of the same expression type as the user and a record of a different expression type from the user; and then searching for the record with the same expression type as the user from the third record information, namely ensuring that the user intention is the same firstly and then embracing the expression type to be the same.
Of course, the user intention and the expression habit may be searched at the same time, and the final first recorded information may be directly obtained and output.
In addition, when searching for the record information of the same expression type as the user, the following specific steps may be performed: and searching the recorded information which is the same as or similar to the expression type of the user, namely, only one expression type which is in accordance with the user can be found in the word habit and the expression mode.
Further, the method also comprises the following steps: determining standard information which is stored in advance and has similarity with the user intention and meets a fourth condition; outputting first recording information including: and outputting the standard information and the first recorded information as an output result so that the user can confirm whether the first recorded information is matched with the input information and confirm whether the standard information is matched with the input information.
If the user inputs information, the intelligent customer service system identifies and outputs only the first recorded information as an output result, the user only sees the first recorded information, that is, only outputs a final determination result, but does not output the user intention determined in the process, which may cause that, if the first recorded information does not contain information matched with the input information, the user may continue to input information, at this time, the intelligent customer service system does not know whether the identified user intention is incorrect, whether the finally output first recorded information is different from the expression type of the input information, or whether the finally output first recorded information is not highly similar to the input information.
Therefore, the standard information is output while the first recorded information is output, so that a user can determine which link is identified by error, and the intelligent customer service system can know which link to perform correction again.
The standard information is pre-stored, the similarity between the output standard information and the user intention meets a fourth condition, namely the standard information and the user intention can be equivalent, if the user determines that the standard information output by the intelligent customer service system is correct and the first record information is incorrect, the user intention can be determined to be correct in identification, and then only the record with the similarity between the output standard information and the user intention meeting the first condition needs to be searched continuously from the history record;
if the user determines that the standard information output by the intelligent customer service system is wrong, the first recorded information is also necessary to be wrong, at this moment, the problem that the user intention is identified can be determined, the intelligent customer service system needs to re-identify the input information of the user, re-confirm the user intention, and on the basis, re-search the first recorded information from the historical record until the output first recorded information and the standard information are both correct, the intelligent customer service system can be determined to be completely correct, and at this moment, a solution can be fed back to the user based on the input information of the user only to be correct.
The information processing system disclosed in this embodiment acquires input information of a user, identifies the input information to determine user intention, searches, as first record information, record information whose similarity to the user intention satisfies a first condition from a history, and outputs the first record information to enable the user to determine whether the first record information matches the input information, where the history is input information of a plurality of users stored in advance. According to the scheme, after the input information of the user is acquired, the intention of the user is confirmed, the record meeting the condition of the similarity with the intention of the user is searched from the historical record, and the searched record is output, the record information meeting the first condition of the similarity with the intention of the user is output, the record information is the input information meeting the input habit of the user, and the user can more accurately and definitely determine whether the input information meeting the input habit of the user is matched with the input information of the user instead of directly outputting the standard problem, so that the problem of poor communication caused by the fact that the user cannot understand the standard problem is solved.
The embodiment discloses an electronic device, a schematic structural diagram of which is shown in fig. 5, and the electronic device includes:
a processor 51 and a memory 52.
The processor 51 is configured to obtain input information of a user, identify the input information to determine a user intention, search, from a history, record information whose similarity to the user intention satisfies a first condition as first record information, and output the first record information to enable the user to determine whether the first record information matches the input information;
the memory 52 is used for storing a history, which is input information of a plurality of users stored in advance.
The electronic device disclosed in this embodiment is implemented on the basis of the information processing method disclosed in the above embodiment, and details are not described here.
The electronic device disclosed in this embodiment acquires input information of a user, identifies the input information to determine user intention, searches record information having similarity to the user intention that satisfies a first condition from a history record as first record information, and outputs the first record information to enable the user to determine whether the first record information matches the input information, where the history record is input information of a plurality of users stored in advance. According to the scheme, after the input information of the user is acquired, the intention of the user is confirmed, the record meeting the condition of the similarity with the intention of the user is searched from the historical record, and the searched record is output, the record information meeting the first condition of the similarity with the intention of the user is output, the record information is the input information meeting the input habit of the user, and the user can more accurately and definitely determine whether the input information meeting the input habit of the user is matched with the input information of the user instead of directly outputting the standard problem, so that the problem of poor communication caused by the fact that the user cannot understand the standard problem is solved.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An information processing method comprising:
acquiring input information of a user;
identifying the input information to determine a user intent;
searching record information with the similarity meeting a first condition with the user intention from a historical record as first record information, and outputting the first record information to enable the user to determine whether the first record information is matched with the input information;
wherein the history is input information of a plurality of users stored in advance.
2. The method of claim 1, further comprising:
and determining whether the user intention meets a second condition, and if the user intention meets the second condition, searching the record information with the similarity meeting the first condition with the user intention from the history record as first record information.
3. The method of claim 1, further comprising:
identifying the input information to determine the expression type of the user;
the searching for record information with similarity to the user intention meeting a first condition from a history record as first record information and outputting the first record information includes:
and searching the historical record for record information meeting the condition of similarity with the user intention and the expression type of the user as first record information, and outputting the first record information.
4. The method according to claim 3, wherein the searching for, from the history, record information whose similarity to the user's intention and the user's expression type satisfies a condition as first record information, and outputting the first record information comprises:
searching record information meeting a third condition with the expression type of the user from a historical record as second record information;
and searching the second recording information for recording information with the similarity meeting a first condition with the user intention as first recording information, and outputting the first recording information.
5. The method according to claim 3, wherein the searching for, from the history, record information whose similarity to the user's intention and the user's expression type satisfies a condition as first record information, and outputting the first record information comprises:
searching record information with the similarity meeting a first condition with the user intention from a historical record as third record information;
and searching the third record information for record information meeting a third condition with the expression type of the user as first record information, and outputting the first record information.
6. The method according to claim 1, wherein the searching for, from the history, the record information whose similarity to the user intention satisfies a first condition as first record information, and outputting the first record information comprises:
searching record information with the similarity meeting a first condition with the user intention from a historical record;
and if the number of the record information with the similarity meeting the first condition is not less than 2, performing priority arrangement on the not less than 2 record information according to the similarity, taking the arranged not less than 2 record information as first record information, and outputting the first record information.
7. The method of claim 1, further comprising:
determining standard information which is stored in advance and has the similarity with the user intention and meets a fourth condition;
the outputting the first recording information includes:
and outputting the standard information and the first recorded information as an output result so that a user can confirm whether the first recorded information is matched with the input information and confirm whether the standard information is matched with the input information.
8. An information processing system comprising:
an acquisition unit configured to acquire input information of a user;
an identification unit for identifying the input information to determine a user intention;
an output unit configured to search a history for a record whose similarity to the user intention satisfies a first condition as first record information, and output the first record information so that the user determines whether the first record information matches the input information;
wherein the history is input information of a plurality of users stored in advance.
9. The system of claim 8, further comprising:
and the determining unit is used for determining whether the user intention meets a second condition, and if the user intention meets the second condition, searching the record information with the similarity meeting the first condition with the user intention from the history record as first record information.
10. An electronic device, comprising:
the processor is used for acquiring input information of a user, identifying the input information to determine user intention, searching record information with similarity meeting a first condition with the user intention from a historical record to serve as first record information, and outputting the first record information to enable the user to determine whether the first record information is matched with the input information;
and the memory is used for storing the history records, and the history records are pre-stored input information of a plurality of users.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911425098.4A CN111222043A (en) | 2019-12-31 | 2019-12-31 | Information processing method and system and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911425098.4A CN111222043A (en) | 2019-12-31 | 2019-12-31 | Information processing method and system and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111222043A true CN111222043A (en) | 2020-06-02 |
Family
ID=70810688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911425098.4A Pending CN111222043A (en) | 2019-12-31 | 2019-12-31 | Information processing method and system and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111222043A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140188847A1 (en) * | 2012-12-27 | 2014-07-03 | Industrial Technology Research Institute | Interactive object retrieval method and system |
| CN107609101A (en) * | 2017-09-11 | 2018-01-19 | 远光软件股份有限公司 | Intelligent interactive method, equipment and storage medium |
| CN108121713A (en) * | 2016-11-28 | 2018-06-05 | 渡鸦科技（北京）有限责任公司 | Intension recognizing method and device |
| CN109992654A (en) * | 2019-03-27 | 2019-07-09 | 联想(北京)有限公司 | A kind of information processing method and computer readable storage medium |
-
2019
- 2019-12-31 CN CN201911425098.4A patent/CN111222043A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140188847A1 (en) * | 2012-12-27 | 2014-07-03 | Industrial Technology Research Institute | Interactive object retrieval method and system |
| CN108121713A (en) * | 2016-11-28 | 2018-06-05 | 渡鸦科技（北京）有限责任公司 | Intension recognizing method and device |
| CN107609101A (en) * | 2017-09-11 | 2018-01-19 | 远光软件股份有限公司 | Intelligent interactive method, equipment and storage medium |
| CN109992654A (en) * | 2019-03-27 | 2019-07-09 | 联想(北京)有限公司 | A kind of information processing method and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111046152B (en) | Automatic FAQ question-answer pair construction method and device, computer equipment and storage medium | |
| CN108491433B (en) | Chat response method, electronic device and storage medium | |
| CN107797984B (en) | Intelligent interaction method, equipment and storage medium | |
| EP3567498A1 (en) | Method and device for question response | |
| CN108388558B (en) | Question matching method and device, customer service robot and storage medium | |
| US20090089282A1 (en) | Natural language based service selection system and method, service query system and method | |
| CN110874401B (en) | Information processing method, model training method, device, terminal and computing equipment | |
| CN109992601B (en) | To-do information pushing method and device and computer equipment | |
| CN108121455B (en) | Identification correction method and device | |
| CN110209790B (en) | Question-answer matching method and device | |
| CN111597313B (en) | Question answering method, device, computer equipment and storage medium | |
| CN110781280A (en) | Knowledge graph-based voice assisting method and device | |
| CN113064980A (en) | Intelligent question and answer method and device, computer equipment and storage medium | |
| CN109522397B (en) | Information processing method and device | |
| CN110765342A (en) | Information query method and device, storage medium and intelligent terminal | |
| CN112487810A (en) | Intelligent customer service method, device, equipment and storage medium | |
| CN107992210A (en) | Input method vocabulary recommends method, intelligent terminal and the device with store function | |
| CN112182186A (en) | Intelligent customer service operation method, device and system | |
| CN111324705A (en) | System and method for adaptively adjusting related search terms | |
| CN111639160A (en) | Domain identification method, interaction method, electronic device and storage medium | |
| CN111222043A (en) | Information processing method and system and electronic equipment | |
| CN112749530B (en) | Text encoding method, apparatus, device and computer readable storage medium | |
| CN114281942A (en) | Question and answer processing method, related equipment and readable storage medium | |
| CN116415063A (en) | Cloud service recommendation method and device | |
| CN112395402A (en) | Depth model-based recommended word generation method and device and computer equipment |
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 |