CN108335110B - Chat information processing method and device - Google Patents
Chat information processing method and device Download PDFInfo
- Publication number
- CN108335110B CN108335110B CN201710031872.8A CN201710031872A CN108335110B CN 108335110 B CN108335110 B CN 108335110B CN 201710031872 A CN201710031872 A CN 201710031872A CN 108335110 B CN108335110 B CN 108335110B
- Authority
- CN
- China
- Prior art keywords
- user
- content
- question
- determining
- category
- 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.)
- Active
Links
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
Abstract
The embodiment of the application discloses a chat information processing method and a chat information processing device, wherein the method comprises the following steps: the server determines chat record content to be analyzed and preset classification rule information, wherein the chat record content comprises a plurality of conversation content items which are input by a first user and are related to question consultation; determining the problem category to which the conversation content item belongs by using the classification rule information; and counting the dialog content items of each question category and providing a statistical result. Through the embodiment of the application, the conversation content items of the consultation problems input by the first user can be classified and statistically analyzed in an automatic mode, the statistical result can be provided for the second user or operators and the like, manual statistical analysis work does not need to be carried out by means of a large number of operators, the statistical efficiency can be improved, and the labor cost and the time cost can be reduced.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to a chat information processing method and apparatus.
Background
With the continuous improvement of electronic commerce transaction platforms and the rapid development of traditional communication, mobile communication and other technologies, more and more people acquire commodities required in daily life in an online shopping mode. In the e-commerce transaction platform system, a system platform operator, a consumer or buyer user (which may be referred to as a first user, and may browse information of a business object published by a merchant or a seller user through a client or a web page and make a purchase, etc.), a merchant or a seller user (which may be referred to as a second user, and may publish a business object sold by the second user through the platform and provide detailed information about the business object, etc.) may be included.
In the operation process of the e-commerce transaction platform, when a first user encounters some technical problems, business problems and the like, the first user can communicate with a customer service staff of a second user or a technical staff of the system platform through the instant messaging application to seek a solution, for example, when the first user wants to purchase a certain business object in a second user shop, if a phenomenon of flash back always occurs when a relevant link is clicked, the phenomenon can be fed back to the relevant technical staff of the system platform so as to solve the phenomenon; for another example, when the first user wants to purchase a business object in the second user's store, and wants the price to be more favorable, the first user can communicate with the customer service staff in the second user's store to inquire whether the price of the business object can be adjusted lower, and so on.
At present, some electronic commerce transaction platforms hope to perform statistics on chat record contents generated in the chat process according to certain requirements (for example, performing classification statistics on problems raised by a first user, and the like) so as to optimize the platforms, usually, an operator performs manual statistical analysis on the chat record contents to obtain statistical results, and because the data volume contained in the chat record contents is very large, a large amount of time is consumed by the operator to obtain corresponding statistical results, so that the statistical efficiency is low, and the labor cost and the time cost are high.
In summary, how to improve the statistical efficiency of the chat record content generated during the operation of the electronic commerce transaction platform becomes a technical problem to be solved by those skilled in the art.
Disclosure of Invention
The application provides a chat information processing method and device, which can improve the statistical efficiency of chat record contents generated in the operation process of an e-commerce transaction platform and save the labor cost and the time cost.
The application provides the following scheme:
a chat record information processing method comprises the following steps:
the server determines chat record content to be analyzed and preset classification rule information, wherein the chat record content comprises a plurality of conversation content items which are input by a first user and are related to question consultation;
determining the problem category to which the conversation content item belongs by using the classification rule information;
and counting the dialog content items of each question category and providing a statistical result.
A chat record information processing method comprises the following steps:
the client determines a chat record file to be analyzed;
and generating an analysis request according to the chat record file to be analyzed, submitting the analysis request to a server, determining the chat record content to be analyzed and preset classification rule information by the server, determining the problem category to which the conversation content item belongs by using the classification rule information, counting the conversation content items of each problem category, and providing a statistical result.
A chat record information processing device is applied to a server and comprises:
the system comprises a content and information determining unit, a query and analysis unit and a query and analysis unit, wherein the content and information determining unit is used for determining chat record content to be analyzed and preset classification rule information, and the chat record content comprises a plurality of conversation content items which are input by a first user and are related to question consultation;
a question category determining unit configured to determine a question category to which the conversation content item belongs, using the classification rule information;
and the statistical unit is used for counting the dialogue content items of each question category and providing a statistical result.
A chat record information processing device is applied to a client and comprises:
the chat record file determining unit is used for determining the chat record file to be analyzed;
and the analysis request submitting unit is used for generating an analysis request according to the chat record file to be analyzed, submitting the analysis request to a server, determining the chat record content to be analyzed and preset classification rule information by the server, determining the problem category to which the conversation content item belongs by using the classification rule information, counting the conversation content items of each problem category, and providing a statistical result.
According to the specific embodiments provided herein, the present application discloses the following technical effects:
according to the embodiment of the application, the chat record content to be analyzed (including a plurality of conversation content items related to problem consultation input by a first user) and the preset classification rule information can be determined, the classification rule information is utilized to determine the problem types to which the conversation content items belong, then the conversation content items of all the problem types are counted and the statistical result is provided, so that the conversation content items of the consultation problems input by the first user can be classified and statistically analyzed in an automatic mode, the statistical result can be provided for a second user or an operator and the like, manual statistical analysis work does not need to be carried out by a large number of operators, the statistical efficiency can be improved, and the labor cost and the time cost can be reduced.
Of course, it is not necessary for any product to achieve all of the above-described advantages at the same time for the practice of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a block diagram of a system provided by an embodiment of the present application;
FIG. 2 is a flow chart of a first method provided by an embodiment of the present application;
FIG. 3 is a flow chart of a second method provided by embodiments of the present application;
FIG. 4 is a schematic diagram of a first apparatus provided by an embodiment of the present application;
fig. 5 is a schematic diagram of a second apparatus provided 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 that can be derived from the embodiments given herein by a person of ordinary skill in the art are intended to be within the scope of the present disclosure.
In order to improve the efficiency of performing statistics on the first user consultation problems in the chat record content, referring to fig. 1, an embodiment of the present application provides a chat record information processing system, where a user targeted by the system may be a second user (e.g., a merchant or a seller user), or may also be a system operator, that is, a client may be provided for the second user or the system operator, and the client may be installed and used in a terminal device thereof to analyze an assigned chat record file, view a specific statistical result, and improve and optimize a service object or a system and the like according to the statistical result. In addition, the system can also comprise a server, during the concrete implementation, the client can specify the chat record file to be analyzed, the server can firstly determine the chat record content to be analyzed (which comprises a plurality of dialogue content items related to the question consultation and input by the first user) and preset classification rule information, and then determine the question category to which the dialogue content items belong by using the classification rule information, then, the dialogue content items of each question category are counted and a statistical result is provided, so that the dialogue content items of the consultation questions input by the first user can be classified and statistically analyzed in an automatic mode, the statistical result can be provided for a second user or an operator and the like, and the manual statistical analysis work does not need to be carried out by a large number of operators, so that the statistical efficiency can be improved, and the labor cost and the time cost can be greatly reduced.
Specific implementations are described in detail below.
Example one
Referring to fig. 2, the first embodiment provides a chat log information processing method from the perspective of a server, and may include the following steps:
s201, the server determines chat record content to be analyzed and preset classification rule information.
Wherein, the chat record content can include a plurality of conversation content items related to the question consultation input by the first user (for example, a consumer user or a buyer user).
In a specific implementation, the chat record content can be different according to different application scenes. For example, in an application scenario facing a second user, the chat log content to be analyzed may include chat log content generated during a chat between the first user and the second user, and the dialog content entry related to the question consultation may include: a question consulting related to the business object associated with the second user is consulted with the associated conversation content item. Here, the so-called business object may be a shop object or a commodity object of the second user, or the like. In practical application, in the process of browsing or purchasing, if a certain business object has a question, a first user may initiate a conversation with a customer service staff of a second user through an interface provided in a page or an independent instant messaging tool, and the like, and the first user may input a text to describe the question and the customer service staff of the second user answers. During such a conversation, chat log content can be generated.
In an application scenario facing to a system operator, the chat log content to be analyzed may include chat log content generated during a chat process between the first user and the system operator, and the dialog content entry related to the issue consultation may include a dialog content entry related to a technical issue consultation. In practical application, the sales platform may provide an entry for the first user to perform a conversation with the system operator in multiple ways, and if the first user finds some technical problems in the process of using the sales platform, for example, there is a problem that a refresh rate is slow when a certain page is opened, or a program automatically exits a problem when a certain operation is performed, and the like, the first user may enter an interface for performing a conversation with the system operator through the entry, describe a problem that the first user needs to consult in an edit box of the interface, and the system operator may reply after receiving the question, and the like. Thus, chat log content can also be generated for this type of conversation.
In practical applications, the chat record content may be recorded by the instant messaging server, or may be recorded locally at the terminal device at the client of each user, and so on. In the embodiment of the application, the chat record content can be downloaded from the server in advance and used as a data source to be analyzed, or if the chat record content is also stored locally in the terminal device, the chat record content can also be directly read locally from the terminal device. The chat log content is a record generated in the process of a double-talk session, and therefore, the chat log content is usually composed of a single session content entry, and when the chat log is saved, there are various specific saving forms, for example, saving in the form of a file, and the like. Among them, for such chat log content existing in the form of a file, the file is generally called a chat log file, in which a plurality of conversation content entries, and information such as speaker identification and speaking time corresponding to each entry are stored. Therefore, in the embodiment of the present application, the chat log file to be analyzed may be determined, and then the dialog content item related to the question inquiry input by the first user is extracted from the chat log file to determine the chat log content to be analyzed. The chat log file can be downloaded from a server in advance or stored in the local of the terminal device in advance, and in short, when analysis is needed, the chat log file can be prepared in advance and used as input data of a specific statistical analysis module.
It should be noted that, since the chat log content has an attribute of generation time, theoretically, from when the second user issues a business object such as a shop or a commodity, if the second user has his/her own customer service person, a chat log may be generated with the first user, and a new chat log may be continuously generated. The same applies to the content of the chat log between the first user and the system operator, i.e. the content of the chat log may increase over time. In the embodiment of the present application, analysis statistics may be performed on the content of the historical chat records in a specified time period, for example, analysis statistics may be performed on the content of the chat records in the last month, or analysis statistics may be performed on the content of the chat records in the last week, or a start time and an end time of the analysis may also be specified, for example, analysis may be performed on the chat records generated between 4 months and 1 day and 4 months and 30 days, and the like. The above configuration information can be set by the user of the system according to the actual requirement.
If the data source input by the user is a chat log file, since the chat log file usually includes various information including sender information, sending time information, and the like of each conversation content item, and the conversation content items of both conversation parties are included, while in the embodiment of the present application, only the analysis and statistics of the question text in the process of asking questions of the first user are needed, the conversation content items related to answers and the like of the second user client service staff or the system operator in the process of the conversation, and the greetings, the closing words, and the like between both conversation parties belong to useless data in practice, so that in the specific implementation, a plurality of conversation content items related to question consultation input by the first user can be extracted from the chat log file at first.
In a specific implementation, in order to achieve the above extraction purpose, it can be implemented in various ways, for example, the useless data can be first eliminated, so that the dialog content items related to the question consultation, which are input by the first user and are required in the embodiment of the present application, remain. In particular, when the useless data is removed, there may be a plurality of implementation manners, for example, in one of the manners, the dialog content entry input by the second user client service personnel or the system operator may be removed first. In a specific implementation, since the chat log file includes the sender information of each dialog content entry, and the numbers of the second user customer service staff and the system operator are relatively fixed, for example, a certain second user may provide six customer service staff, and the like, and the identifications of accounts, IDs, and the like of these staff may be known to the user in advance, so that, for the purpose of eliminating this part of data, the user may set in advance service staff list information for recording identification information (such as a user ID, and the like) of the service staff having a dialog with the first user, where the service staff may include service staff of the second user, the system operator, and the like. In this way, because the chat log file may include the dialog text content and the speaker identification information (such as the user ID, etc.), the dialog content entry corresponding to the entry whose speaker identification matches the identification information recorded in the service staff list in the chat log file may be deleted, that is, the dialog content input by the customer service staff of the second user may be deleted, or the dialog content input by the system operator may be deleted.
After the dialogue content input by the service personnel is deleted, the remaining dialogue content can be regarded as the dialogue content input by the first user, so that the dialogue content item input by the first user and related to the problem consultation can be determined according to the remaining dialogue content.
As described above, some dialog contents such as greeting, closing, etc. may exist in the dialog content entry, such as a dialog content entry where the first user and the service person are engaged in a small talk (e.g., "hello", "doing so", etc.), and thus, after the dialog content input by the service person is deleted, some useless data irrelevant to the problem consultation may be included in the remaining dialog content. Various implementations are possible for culling the unwanted data. For example, in a specific implementation manner, a useless data elimination rule may be preset, and the preset useless data elimination rule is used to delete the dialog entry irrelevant to the question consultation in the remaining dialog content, so as to obtain the dialog content entry relevant to the question consultation input by the first user, so as to reduce the data amount in the subsequent statistical analysis step, save the system overhead, and improve the statistical efficiency.
In specific implementation, a regular expression corresponding to the garbage elimination rule may be preset, and for example, the regular expression may be: ' \ s? \\ S + \? Is? Instant message \ s? [ \ S ]? And matching the regular expression in the rest dialogue content, determining dialogue entries matched with the regular expression as useless data, and eliminating the dialogue entries so as to achieve the aim of deleting the dialogue entries irrelevant to the problem consultation.
Of course, in other implementations, the above useless data related to the greeting and the like may be removed, and then the dialog content entry input by the service personnel may be removed, and so on, which will not be described in detail herein.
S202, determining the problem category to which the conversation content item belongs by using the classification rule information.
After the items of conversation content input by the first user and related to the question consultation are determined, the items of conversation content can be classified so as to determine the question category to which each item of conversation content belongs. To achieve this, a classification rule may be set in advance, and classification may be performed according to the rule. The specific classification rule may be various, in a specific implementation manner, the classification rule information may include keyword information associated with each question category, where the keyword may be, for example, "return for goods," "refund," "deliver for goods," and the like, and the keyword information associated with each question category may be stored in a file or the like, for example, the content specifically stored in the file may be as shown in table 1:
TABLE 1
| Serial number | Problem category | Keyword |
| 1 | Class 1 | Keyword A |
| 2 | Class 2 | Keyword B |
| …… | …… | …… |
In the case where the above-described keyword file is provided, it may be determined whether or not a certain keyword exists in the dialog content item, and if a certain keyword exists, the problem category to which the dialog content item belongs may be determined, for example, by referring to table 1, based on the certain keyword.
In another specific implementation manner, the classification rule may further include a regular expression associated with each question category.
In specific implementation, what expression mode is generally adopted by the first user to perform specific problem description when consulting each problem category can be summarized according to experience in advance, corresponding text format features are extracted according to the expression modes, and then corresponding regular expressions can be generated according to the text format features of the specific problem description texts under each problem category.
For example, when the first user expresses that the user wants to "return goods", the user usually adopts "i want to return XX", "i do not want XX", and the like, so that corresponding text format features can be extracted from the expression modes about "return goods", and then regular expressions corresponding to the problem category of "return goods" are generated according to the text format features. Since there may be one or more expressions for consulting the same problem category, at least one regular expression may be associated with each problem category.
In specific implementation, each question category and its associated regular expression may also be stored in the keyword file, and thus, the content stored in the keyword file may be as shown in table 2:
TABLE 2
Thus, the associated regular expression may be determined by querying table 2 for the question category associated with the keyword. The regular expression may be in the form of: ' \\ n \ d {4} year \ d \ d \ d month \ d \ d \ d day \ d \ d: \ d \ d? ([: \ s ] +.
Specifically, when determining the problem category to which the dialog content entry belongs, whether the dialog content entry hits a regular expression or not may be determined in a traversal form, and if the dialog content entry hits a regular expression, it may be determined that the dialog content entry belongs to the problem category corresponding to the regular expression.
Of course, in other specific implementations, there may be other ways to determine the question category to which the dialog content item belongs, and the details are not described here.
S203, counting the dialogue content items of each question category and providing a counting result.
In practical application, statistics can be performed according to actual needs to obtain corresponding statistical results, for example, first users corresponding to dialog content items included in each problem category can be determined, and the number of first users corresponding to each problem category, such as the number of first users who propose "return" and the number of first users who propose "page flash back", etc., is counted, so that when the number of first users corresponding to a certain problem category reaches a predetermined number, the problem is solved in time, and business objects in stores, functions of system platforms, etc., are improved and optimized.
For another example, the ratio of the first user number included in each question category to the first user number participating in the question may be counted, for example, the ratio of the first user number proposing "refund" to the first user number participating in the question, the ratio of the first user number proposing "page messy code" to the first user number participating in the question, and the like, so as to improve and optimize the business objects in the shop, the functions of the system platform, and the like.
In practical application, in an application scene facing a second user, the system can provide the statistical result to the second user client, so that the second user can improve the problems of the business objects by using the statistical result, and the purpose of optimizing the business objects in the shop is achieved; in an application scenario facing system operators, the statistical result can be provided to the system operators, so that the system operators can improve the problems in the technical aspect by using the statistical result, and the purpose of optimizing the system is achieved.
Through the embodiment of the application, the problem categories can be determined and the statistical analysis can be carried out on the dialogue content items of the consultation problems input by the first user in an automatic mode, the statistical result can be provided for the second user or operators and the like, manual statistical analysis work does not need to be carried out by means of a large number of operators, the statistical efficiency can be improved, and the labor cost and the time cost can be greatly reduced.
In addition, because the first user makes a consultation based on the problems of the business objects purchased by the first user, when the chat record information processing system faces the second user, a more detailed statistical result can be provided for the second user according to different business objects, so that the second user can know the problems of the specific business objects in the shop in time, and the specific business objects can be improved, optimized and the like in a more targeted manner according to the problem conditions.
In a specific implementation, the problem inquiry issued by the first user is usually related to a business object which is being purchased or is purchased recently, and the sales platform usually records the historical transaction information of the first user, that is, the chat record content and the historical transaction record often have a certain correlation. Therefore, the business object associated with the specific dialog content item can be determined by utilizing the relevance, and then the specific problem category is analyzed and counted from the business object. In specific implementation, a time period to which the chat record to be analyzed belongs may be determined, historical transaction record information generated by the first user in the corresponding time period may be extracted, then a service object associated with the dialog content entry related to the problem consultation and input by the first user may be determined according to the historical transaction record information, and then the dialog content entry related to the problem consultation and input by the first user may be divided into a plurality of groups according to different associated service objects, that is, the dialog content entries may be grouped by taking each service object as a unit.
Then, the dialog content items can be classified by using the classification rule information in the group of dialog content items related to each business object, and the dialog content items of each question category are counted in the group of dialog content items corresponding to each business object, and a counting result for the dialog content items related to each business object is provided. Therefore, the system can provide a statistical result aiming at each business object for the second user according to the difference of the business objects, is more beneficial to the second user to know the problems of the business objects in the shop of the second user based on the more detailed statistical result, can improve and optimize the business objects according to the problem conditions, and can improve the automation degree of the system.
Furthermore, because the process of selling the business object by the second user usually comprises two stages of pre-sale and post-sale, when the chat record information processing system faces the second user, the chat record information processing system can provide further refined statistical results for the second user according to different sales stages, so that the second user can know the problems of the business object in the shop, and the business object can be improved, optimized and the like according to the problem conditions.
Specifically, the preset service staff list may include a first sales stage service staff list representing a chat between a second user and the first user, and a second sales stage service staff list, in this embodiment, the first sales stage may also be referred to as pre-sales, and the second sales stage may also be referred to as post-sales.
Based on this, the conversation content items input by the first user and related to the problem consultation can be grouped to obtain the conversation content items input by the first user and related to the problem consultation in the chatting process of the first sales stage service personnel, and the conversation content items input by the first user and related to the problem consultation in the chatting process of the second sales stage service personnel, that is, the conversation content items input by the first user and related to the problem consultation are divided into two groups, one group is the conversation content items related to the problem consultation generated in the chatting process of the second user pre-sales service personnel, and the other group is the conversation content items related to the problem consultation generated in the chatting process of the second user post-sales service personnel.
Then, in the above-mentioned conversation content item with the pre-sale service personnel and the conversation content item with the after-sale service personnel respectively, the said conversation content item is classified by using the said classification rule information, and in the above-mentioned conversation content item with the pre-sale service personnel and the conversation content item with the after-sale service personnel respectively, the conversation content item of each question category is counted, and the statistical result of the conversation content item with the pre-sale service personnel and the statistical result of the conversation content item with the after-sale service personnel are provided, so that the system can provide the second user with the question that the business object respectively exists before and after sale according to the different sale stages, based on the further refined statistical result, the second user can know the question that the business object exists in the shop, and can improve the business object according to the question situation, Optimization and the like, and further improves the automation degree of the system.
Example two
The second embodiment corresponds to the first embodiment, and from the perspective of the client (which may include a second user client, or a system operator client, etc.), a chat record information processing method is provided, and referring to fig. 3, the method may include the following steps:
s301: the client determines a chat record file to be analyzed;
s302: and generating an analysis request according to the chat record file to be analyzed, submitting the analysis request to a server, determining the chat record content to be analyzed and preset classification rule information by the server, determining the problem category to which the conversation content item belongs by using the classification rule information, counting the conversation content items of each problem category, and providing a statistical result.
Since the second embodiment corresponds to the first embodiment, reference may be made to the description in the first embodiment for specific implementation, and details are not described here.
Corresponding to the chat log information processing method provided in the first embodiment, an embodiment of the present application further provides a chat log information processing apparatus, referring to fig. 4, the apparatus may include a content and information determining unit 401, a problem category determining unit 402, and a statistics unit 403, where:
the content and information determining unit 401 may be configured to determine chat record content to be analyzed, where the chat record content includes a plurality of dialog content entries related to question consultation input by the first user, and preset classification rule information.
A question category determining unit 402, configured to determine, by using the classification rule information, a question category to which the dialog content item belongs.
The statistic unit 403 may be configured to perform statistics on the dialog content items of each question category and provide a statistic result.
In a specific implementation, the content and information determining unit 401 may include:
the chat record file determining subunit is used for determining the chat record file to be analyzed;
and the conversation content item extraction subunit is used for extracting the conversation content item which is input by the first user and is related to the question consultation from the chat record file.
The chat log file may include dialog text content and speaker identification information, and based on this, the dialog content entry extraction subunit may be specifically configured to:
determining preset service staff list information, wherein the service staff list is used for recording identification information of service staff having a conversation with the first user;
deleting the conversation content corresponding to the entry in the chat record file, wherein the entry is matched with the identification information recorded in the service personnel list by the speaker identification;
and determining the dialog content items which are input by the first user and are related to the question consultation according to the remaining dialog content.
Further, the dialog content item extraction subunit may be further specifically configured to:
and deleting the conversation items irrelevant to the problem consultation in the residual conversation contents by using a preset useless data removing rule to obtain the conversation content items relevant to the problem consultation and input by the first user.
Wherein the classification rule information may include: based on the keyword information associated with each question category, the question category determining unit 402 may be specifically configured to:
judging whether a keyword exists in the conversation content item or not;
if yes, determining the question category to which the conversation content item belongs according to the keyword.
The classification rule further includes a regular expression associated with each question category, the regular expression is generated according to text format features of a specific question description text under each question category, and based on this, the question category determining unit 402 may be specifically configured to:
determining a related regular expression according to the problem category related to the keyword;
and judging whether the conversation content item hits the regular expression associated with the problem category, and if so, determining that the conversation content item belongs to the problem category.
In a specific implementation, the statistical unit 403 may specifically be configured to:
determining first users corresponding to the dialogue content items contained in the question categories;
and counting the number of the first users corresponding to each problem category.
Further, the statistical unit 403 may be further specifically configured to:
and counting the proportion of the number of the first users contained in each question category in the total number of the first users participating in the question.
In practical applications, the preset list of service staff may include a first list of sales stage service staff for chatting with the first user on behalf of the second user, and a second list of sales stage service staff,
the apparatus may further include:
the first grouping unit is used for grouping the conversation content items input by the first user and related to the problem consultation to obtain the conversation content items input by the first user and related to the problem consultation in the chatting process of the first sales stage service personnel and the conversation content items input by the first user and related to the problem consultation in the chatting process of the second sales stage service personnel;
based on this, the problem category determining unit 402 is further configured to:
classifying the dialog content items by using the classification rule information in each group respectively;
the statistic unit 403 may further be configured to:
and respectively counting the dialogue content items of each question category in each group and providing a counting result.
In an application scenario facing a second user, the chat log content to be analyzed includes chat log content generated during a chat process between the first user and the second user, and the dialog content related to the question consultation includes: consulting the relevant conversation content with a question on the business object associated with the second user,
based on this, the apparatus may further include:
and the first statistical result providing unit can be used for providing the statistical result to the second user client so that the second user can improve the problems existing in the aspect of the business object by using the statistical result.
Further, the device may further include:
the time period determining unit is used for determining the time period to which the chat records to be analyzed belong;
the historical transaction record information extraction unit is used for extracting the historical transaction record information generated by the first user in a corresponding time period;
the business object determining unit is used for determining a business object which is input by the first user and is associated with a conversation content item related to the problem consultation according to the historical transaction record information;
the second grouping unit is used for dividing the dialogue content items which are input by the first user and are related to the question consultation into a plurality of groups according to different associated business objects;
based on this, the problem category determining unit 402 is further configured to:
classifying the dialog content items by using the classification rule information in each group respectively;
the statistic unit 403 may further be configured to:
and respectively counting the dialogue content items of each question category in each group and providing a counting result.
In an application scenario facing to a system platform side technician, the chat record content to be analyzed includes chat record content generated in a process of chatting between a first user and the platform side technician, and the conversation content related to question consultation includes: dialog contents related to technical problem consultation,
based on this, the apparatus may further include:
and the second statistical result providing unit is used for providing the statistical result to the platform side technical personnel so that the platform side technical personnel can improve the technical problems by using the statistical result.
Corresponding to the second embodiment, an embodiment of the present application further provides a chat log information processing apparatus, referring to fig. 5, where the apparatus is applied to a client, and specifically may include:
a chat log file determining unit 501, configured to determine a chat log file to be analyzed;
an analysis request submitting unit 502, configured to generate an analysis request according to the chat record file to be analyzed, and submit the analysis request to a server, where the server generates and determines chat record content to be analyzed and preset classification rule information, and determines a question category to which the conversation content entry belongs by using the classification rule information, and performs statistics on the conversation content entry of each question category, and provides a statistical result.
The chat information processing device provided by the embodiment of the application can determine chat record contents to be analyzed (including a plurality of dialogue content items related to problem consultation input by a first user) and preset classification rule information, then determine the problem types to which the dialogue content items belong by utilizing the classification rule information, then count the dialogue content items of each problem type and provide a statistical result, thereby classifying and statistically analyzing the dialogue content items of the consultation problems input by the first user in an automatic mode, providing the statistical result for a second user or an operator and the like, and not needing to perform manual statistical analysis by means of a large number of operators, thereby improving the statistical efficiency and greatly reducing the labor cost and the time cost.
From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The chat information processing method and device provided by the application are introduced in detail, and a specific example is applied in the text to explain the principle and the implementation of the application, and the description of the embodiment is only used for helping to understand the method and the core idea of the application; meanwhile, for a person skilled in the art, according to the idea of the present application, the specific embodiments and the application range may be changed. In view of the above, the description should not be taken as limiting the application.
Claims (15)
1. A chat record information processing method is characterized by comprising the following steps:
the server determines chat record content to be analyzed and preset classification rule information, wherein the chat record content comprises a plurality of conversation content items which are input by a first user and are related to question consultation;
determining the problem category to which the conversation content item belongs by using the classification rule information;
and counting the dialog content items of each question category and providing a statistical result.
2. The method of claim 1, wherein determining chat log content to be analyzed comprises:
determining a chat record file to be analyzed;
and extracting the conversation content items which are input by the first user and are related to the question consultation from the chat record file.
3. The method of claim 2, wherein the chat log file comprises dialog text content and speaker identification information, and wherein the extracting a plurality of dialog content entries related to question consultation input by the first user from the chat log file comprises:
determining preset service staff list information, wherein the service staff list is used for recording identification information of service staff having a conversation with the first user;
deleting the conversation content corresponding to the entry in the chat record file, wherein the entry is matched with the identification information recorded in the service personnel list by the speaker identification;
and determining the dialog content items which are input by the first user and are related to the question consultation according to the remaining dialog content.
4. The method of claim 3, wherein determining the dialog content items related to the question consultation input by the first user according to the remaining dialog content comprises:
and deleting the conversation items irrelevant to the problem consultation in the residual conversation contents by using a preset useless data removing rule to obtain the conversation content items relevant to the problem consultation and input by the first user.
5. The method of claim 3, wherein the preset list of service people comprises a first list of sales stage service people who chat with the first user on behalf of a second user, and a second list of sales stage service people, the method further comprising:
grouping the dialogue content items input by the first user and related to the problem consultation to obtain the dialogue content items input by the first user and related to the problem consultation in the chatting process of the first sales stage service personnel and the dialogue content items input by the first user and related to the problem consultation in the chatting process of the second sales stage service personnel;
the determining the question category to which the dialog content item belongs by using the classification rule information includes:
respectively determining the problem category to which the conversation content item belongs by utilizing the classification rule information in each group;
the counting of the dialog content items of each question category and the providing of the statistical result comprise:
and respectively counting the dialogue content items of each question category in each group and providing a counting result.
6. The method of claim 1, wherein the chat log content to be analyzed comprises chat log content generated during a chat between the first user and the second user, and the dialog content related to the question consultation comprises: dialog content related to a problem consultation on a business object associated with a second user, the method further comprising:
and providing the statistical result to the second user client so that the second user can improve the problems existing in the aspect of the service object by using the statistical result.
7. The method of claim 6, further comprising:
determining the time period to which the chat records to be analyzed belong;
extracting historical transaction record information generated by the first user in a corresponding time period;
determining a business object which is input by the first user and is associated with a dialogue content item related to problem consultation according to the historical transaction record information;
dividing the dialogue content items related to the problem consultation input by the first user into a plurality of groups according to different associated business objects;
the determining the question category to which the dialog content item belongs by using the classification rule information includes:
respectively determining the problem category to which the conversation content item belongs by utilizing the classification rule information in each group;
the counting of the dialog content items of each question category and the providing of the statistical result comprise:
and respectively counting the dialogue content items of each question category in each group and providing a counting result.
8. The method of claim 1, wherein the chat log content to be analyzed comprises chat log content generated during a chat process between the first user and a platform technician, and the dialog content related to the question consultation comprises: dialog content relating to a technical problem consultation, the method further comprising:
and providing the statistical result to the platform side technical personnel so that the platform side technical personnel can improve the problems existing in the technical aspect by using the statistical result.
9. The method according to any one of claims 1 to 8, wherein the classification rule information comprises: keyword information associated with each question category;
the determining the question category to which the dialog content item belongs by using the classification rule information includes:
judging whether a keyword exists in the conversation content item or not;
if yes, determining the question category to which the conversation content item belongs according to the keyword.
10. The method according to claim 9, wherein the classification rules further include regular expressions associated with the question categories, the regular expressions being generated according to text format features of specific question description texts under the question categories;
the determining the question category to which the dialogue content item belongs according to the keyword comprises:
determining a related regular expression according to the problem category related to the keyword;
and judging whether the conversation content item hits the regular expression associated with the problem category, and if so, determining that the conversation content item belongs to the problem category.
11. The method according to any one of claims 1 to 8, wherein the counting dialog content items of each question category and providing a statistical result comprises:
determining first users corresponding to the dialogue content items contained in the question categories;
and counting the number of the first users corresponding to each problem category.
12. The method of claim 9, wherein the counting dialog content items for each question category and providing a statistical result further comprises:
and counting the proportion of the number of the first users contained in each question category to the total number of the first users participating in the question.
13. A chat record information processing method is characterized by comprising the following steps:
the client determines a chat record file to be analyzed;
and generating an analysis request according to the chat record file to be analyzed, submitting the analysis request to a server, determining the chat record content to be analyzed and preset classification rule information by the server, determining the problem category to which the conversation content item belongs by using the classification rule information, counting the conversation content items of each problem category, and providing a statistical result.
14. A chat record information processing device is applied to a server and comprises:
the system comprises a content and information determining unit, a query and analysis unit and a query and analysis unit, wherein the content and information determining unit is used for determining chat record content to be analyzed and preset classification rule information, and the chat record content comprises a plurality of conversation content items which are input by a first user and are related to question consultation;
a question category determining unit configured to determine a question category to which the conversation content item belongs, using the classification rule information;
and the statistical unit is used for counting the dialogue content items of each question category and providing a statistical result.
15. A chat log information processing device applied to a client comprises:
the chat record file determining unit is used for determining the chat record file to be analyzed;
and the analysis request submitting unit is used for generating an analysis request according to the chat record file to be analyzed, submitting the analysis request to a server, determining the chat record content to be analyzed and preset classification rule information by the server, determining the problem category to which the conversation content item belongs by using the classification rule information, counting the conversation content items of each problem category, and providing a statistical result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710031872.8A CN108335110B (en) | 2017-01-17 | 2017-01-17 | Chat information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710031872.8A CN108335110B (en) | 2017-01-17 | 2017-01-17 | Chat information processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108335110A CN108335110A (en) | 2018-07-27 |
| CN108335110B true CN108335110B (en) | 2022-04-12 |
Family
ID=62922640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710031872.8A Active CN108335110B (en) | 2017-01-17 | 2017-01-17 | Chat information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108335110B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214854A (en) * | 2018-07-10 | 2019-01-15 | 淘度客电子商务股份有限公司 | A kind of self-help service for user method applied to electric business platform |
| CN109189902B (en) * | 2018-08-09 | 2020-10-16 | 珠海格力电器股份有限公司 | Method and device for automatically answering consultation |
| CN109241256B (en) * | 2018-08-20 | 2022-09-27 | 百度在线网络技术（北京）有限公司 | Dialogue processing method and device, computer equipment and readable storage medium |
| CN111062728B (en) * | 2018-10-17 | 2023-06-30 | 阿里巴巴集团控股有限公司 | Queuing optimization method and device for manual online consultation |
| CN109858021B (en) * | 2019-01-02 | 2023-11-14 | 平安科技（深圳）有限公司 | Service problem statistics method, device, computer equipment and storage medium thereof |
| CN109903134A (en) * | 2019-02-26 | 2019-06-18 | 北京多点在线科技有限公司 | A kind of order automatic generation method and system, storage medium |
| CN111698143B (en) * | 2019-03-14 | 2022-12-16 | 阿里巴巴集团控股有限公司 | Information processing method, information display method and device |
| CN110427473A (en) * | 2019-08-02 | 2019-11-08 | 泰康保险集团股份有限公司 | Data processing method, device, equipment and storage medium |
| CN111192082B (en) * | 2019-12-26 | 2024-03-26 | 广东美的白色家电技术创新中心有限公司 | Product selling point analysis method, terminal equipment and computer readable storage medium |
| CN112434197A (en) * | 2021-01-27 | 2021-03-02 | 博智安全科技股份有限公司 | Reverse extraction method, device, equipment and storage medium of text content |
| CN114706969B (en) * | 2022-05-31 | 2022-09-09 | 深圳追一科技有限公司 | Attention content acquisition method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1770798A (en) * | 2004-10-28 | 2006-05-10 | 中兴通讯股份有限公司 | Method for traffic data gathering and analysis statistic |
| CN103873583A (en) * | 2014-03-24 | 2014-06-18 | 北京聚思信息咨询有限公司 | Method and system for analyzing behaviors of internet users based on cloud platform |
| CN104281607A (en) * | 2013-07-08 | 2015-01-14 | 上海锐英软件技术有限公司 | Microblog hot topic analyzing method |
| CN104731895A (en) * | 2015-03-18 | 2015-06-24 | 北京京东尚科信息技术有限公司 | Auto-answer method and device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101178721A (en) * | 2007-10-12 | 2008-05-14 | 北京拓尔思信息技术有限公司 | Method for classifying and managing useful poser information in forum |
| JP5043735B2 (en) * | 2008-03-28 | 2012-10-10 | インターナショナル・ビジネス・マシーンズ・コーポレーション | Information classification system, information processing apparatus, information classification method, and program |
| CN103167172B (en) * | 2013-02-08 | 2015-02-04 | 广州三星通信技术研究有限公司 | Integration method and system for variety of chat records |
| CN104361003A (en) * | 2014-10-10 | 2015-02-18 | 金硕澳门离岸商业服务有限公司 | Method and device for classified displaying of chat records |
| CN105740382A (en) * | 2016-01-27 | 2016-07-06 | 中山大学 | Aspect classification method for short comment texts |
| CN106095972B (en) * | 2016-06-17 | 2020-06-19 | 联动优势科技有限公司 | Information classification method and device |
-
2017
- 2017-01-17 CN CN201710031872.8A patent/CN108335110B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1770798A (en) * | 2004-10-28 | 2006-05-10 | 中兴通讯股份有限公司 | Method for traffic data gathering and analysis statistic |
| CN104281607A (en) * | 2013-07-08 | 2015-01-14 | 上海锐英软件技术有限公司 | Microblog hot topic analyzing method |
| CN103873583A (en) * | 2014-03-24 | 2014-06-18 | 北京聚思信息咨询有限公司 | Method and system for analyzing behaviors of internet users based on cloud platform |
| CN104731895A (en) * | 2015-03-18 | 2015-06-24 | 北京京东尚科信息技术有限公司 | Auto-answer method and device |
Non-Patent Citations (1)
| Title |
|---|
| 旺旺聊天记录分析;上海宸特电子科技有限公司;《旺旺聊天记录分析》;20130308;第1-4页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108335110A (en) | 2018-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108335110B (en) | Chat information processing method and device | |
| KR100739058B1 (en) | Instant Order System and Method using instant messaging, and Instant Knowledge Service System and Method using instant messaging | |
| US20150371173A1 (en) | Peer to peer chat based commerce system | |
| US20140257987A1 (en) | Method and system for a personalized content dissemination platform | |
| CN104579909B (en) | Method and equipment for classifying user information and acquiring user grouping information | |
| CN110322209A (en) | Comment information processing method, device, system and storage medium | |
| CN110717801A (en) | Commodity information pushing method and device | |
| CN101276450A (en) | Information processing device, information processing method and information processing program | |
| JP7344234B2 (en) | Method and system for automatic call routing without caller intervention using anonymous online user behavior | |
| JP2002297875A (en) | Customer relation management method, system and program | |
| CN110503470B (en) | Operation method and system for product sales promotion | |
| CN112734485A (en) | User intelligent operation system | |
| US20110161135A1 (en) | Method and systems for collateral processing | |
| CN111199473A (en) | Anti-cheating method, device and system based on transaction record information | |
| CN111192045A (en) | Anti-cheating method, device and system based on transaction record information | |
| CN115880077A (en) | Recommendation method and device based on client label, electronic device and storage medium | |
| CN114648389A (en) | Electronic commerce information processing system | |
| CN114638635A (en) | Method and device for determining user rights and interests information | |
| CN112527991A (en) | Information processing method, apparatus and medium | |
| CN111507808A (en) | Commodity pre-selling system based on mobile internet | |
| CN106611365B (en) | Data processing method, device and system | |
| Hsu et al. | Using social listening to evaluate opinion research for social network brand community | |
| JP2013097541A (en) | Outbound marketing system and outbound marketing method | |
| TWM555514U (en) | Sales system and its sales device | |
| Nisafani et al. | Developing Salesperson Performance Indicators on Instant Messaging Platform |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1258190 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |