CN109934631B - Question and answer information processing method and device and computer equipment - Google Patents

Question and answer information processing method and device and computer equipment Download PDF

Info

Publication number
CN109934631B
CN109934631B CN201910188483.5A CN201910188483A CN109934631B CN 109934631 B CN109934631 B CN 109934631B CN 201910188483 A CN201910188483 A CN 201910188483A CN 109934631 B CN109934631 B CN 109934631B
Authority
CN
China
Prior art keywords
attribute
product
target
information
value
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
Application number
CN201910188483.5A
Other languages
Chinese (zh)
Other versions
CN109934631A (en
Inventor
黄玉芳
胡长建
李让
赵建宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lenovo Beijing Ltd
Original Assignee
Lenovo Beijing Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Lenovo Beijing Ltd filed Critical Lenovo Beijing Ltd
Priority to CN201910188483.5A priority Critical patent/CN109934631B/en
Publication of CN109934631A publication Critical patent/CN109934631A/en
Application granted granted Critical
Publication of CN109934631B publication Critical patent/CN109934631B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

After the computer equipment acquires inquiry information of a product, the computer equipment can extract a product attribute which is most concerned by a user, namely a target attribute of the product, and then obtains at least one candidate attribute related to the target attribute by inquiring an attribute relation graph of the product, and further generates and outputs reply information for the user to check based on the respective attribute values of the target attribute and the candidate attribute which the user wants to know. Therefore, the reply information generated by the method and the device can lead the obtained candidate attributes to be different along with the different target attributes contained in the inquiry information, realize the targeted reply to the inquiry content of the user and improve the accuracy and reliability of the reply information.

Description

Question and answer information processing method and device and computer equipment
Technical Field
The present application relates to the field of communications technologies, and in particular, to a method and an apparatus for processing question and answer information, and a computer device.
Background
The intelligent customer service system is an industry-oriented application developed on the basis of large-scale knowledge processing, is suitable for the technical industries of large-scale knowledge processing, natural language understanding, knowledge management, automatic question and answer systems, reasoning and the like, provides a fine-grained knowledge management technology for enterprises, establishes a quick and effective technical means based on natural language for communication between the enterprises and mass users, and can provide statistical analysis information required by fine management for the enterprises, thereby saving a large amount of human resources and cost for the enterprises.
In practical application, aiming at the product attribute inquired by the user, the intelligent customer service system feeds back the attribute value of the product attribute to the user, and simultaneously displays the preset attribute values of a plurality of other attributes as partial reply information in a customer service dialog box to help the user to know the basic information of the product.
However, the inventor has noticed that no matter what attribute of the product is queried by the user, the attribute values of other attributes fed back to the user are fixed and even irrelevant to the product attribute queried by the user, so that the attribute values displayed in the customer service dialog box are not the product attribute situation that the user actually wants to know, the accuracy and flexibility of the response information are reduced, and the actual product query requirement of the user cannot be met.
Disclosure of Invention
In view of this, the present application provides a method, an apparatus, and a computer device for processing question and answer information, which implement a reply to product inquiry information, meet product inquiry requirements, and improve accuracy and flexibility of reply information fed back to a user.
In order to achieve the above object, the present application provides the following technical solutions:
the application provides a question-answer information processing method, which comprises the steps of
Acquiring inquiry information of a product, and extracting target attributes of the product from the inquiry information;
inquiring an attribute relation graph of the product by using the target attribute to obtain at least one candidate attribute of the product, wherein the attribute relation graph comprises correlation coefficients among different attributes of the product;
and generating and outputting reply information aiming at the inquiry information based on the attribute value of the target attribute and the attribute value corresponding to the at least one candidate attribute.
Optionally, the generating and outputting reply information for the query information based on the attribute value of the target attribute and the attribute value corresponding to the at least one candidate attribute includes:
obtaining a product to be compared for the product based on the attribute value of the target attribute;
comparing the attribute values of the same candidate attribute of the product and the product to be compared to obtain a product-level comparison result, wherein the product-level comparison result can indicate the quality of the product and the product to be compared on the at least one candidate attribute;
and generating and outputting reply information aiming at the inquiry information by using the attribute value of the target attribute and the product-level comparison result.
Optionally, the obtaining a product to be compared for the product based on the attribute value of the target attribute includes:
acquiring a reference attribute value of the target attribute of the industry where the product is located;
comparing the attribute value of the target attribute of the product with the reference attribute value to obtain a target attribute comparison result;
and acquiring the product to be compared corresponding to the reference attribute value based on the target attribute comparison result.
Optionally, the generating and outputting reply information for the query information by using the attribute value of the target attribute and the product-level comparison result includes:
determining a target candidate attribute in the at least one candidate attribute according to the product-level comparison result, wherein the target candidate attribute is a candidate attribute of the product superior to the product to be compared;
obtaining reply information aiming at the inquiry information based on the attribute value of the target attribute and the attribute value of the target candidate attribute;
and making and outputting a knowledge card of the product by using the reply information.
Optionally, the obtaining reply information for the query information based on the attribute value of the target attribute and the attribute value of the target candidate attribute includes:
and obtaining reply information aiming at the inquiry information by utilizing the attribute value of the target attribute, the attribute value of the target candidate attribute, a product level comparison result corresponding to the target candidate attribute and/or the target attribute comparison result.
Optionally, the reference attribute value includes an optimal attribute value and a standard attribute value of the target attribute of the industry in which the product is located, and the attribute value of the target attribute of the product is compared with the reference attribute value to obtain a target attribute comparison result; based on the target attribute comparison result, obtaining a product to be compared corresponding to the reference attribute value, including:
calculating a first difference value between the attribute value of the target attribute of the product and the optimal attribute value of the target attribute;
if the absolute value of the first difference is smaller than a first threshold, generating a target attribute comparison result by using the absolute value of the first difference, and acquiring a product to be compared with the optimal attribute value of the target attribute;
if the absolute value of the first difference is not smaller than the first threshold, calculating a second difference between the attribute value of the target attribute of the product and the standard attribute value of the target attribute;
and generating a target attribute comparison result by using the absolute value of the second difference, and acquiring a product to be compared with the standard attribute value of the target attribute.
Optionally, the method further includes:
acquiring product description information of the industry where the product is located;
extracting attributes contained in the product description information;
and constructing an attribute relation graph of the product by using at least two attributes contained in the product description information.
Optionally, the constructing an attribute relationship diagram of the product by using at least two attributes included in the product description information includes:
acquiring a plurality of preset attributes of the product;
establishing an incidence relation between corresponding preset attributes by using at least two attributes contained in the product description information, and determining a correlation coefficient between the corresponding preset attributes;
and constructing an attribute relation graph of the product according to the incidence relation among the preset attributes and the corresponding correlation coefficient.
Optionally, the querying, by using the target attribute, the attribute relationship diagram of the product to obtain at least one candidate attribute of the product includes:
inquiring an attribute relation graph of the product, determining adjacent attributes of the target attribute, and acquiring a correlation coefficient between the target attribute and the adjacent attributes;
and selecting at least one adjacent attribute corresponding to the larger correlation coefficient as a candidate attribute.
Optionally, the method further includes:
acquiring attribute values of different attributes of the same product in the industry of the product;
and calculating the reference attribute value of the corresponding attribute in the industry of the product by using the attribute values of the different attributes.
The application also provides a question-answering information processing device, which comprises
The system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring inquiry information of a product and extracting a target attribute of the product from the inquiry information;
the query module is used for querying an attribute relation graph of the product by using the target attribute to obtain at least one candidate attribute of the product, wherein the attribute relation graph comprises correlation coefficients among different attributes of the product;
and the reply information generation module is used for generating and outputting reply information aiming at the inquiry information based on the attribute value of the target attribute and the attribute value corresponding to the at least one candidate attribute.
Optionally, the reply information generating module includes:
a first obtaining unit configured to obtain a product to be compared for the product based on an attribute value of the target attribute;
the first comparison unit is used for comparing the attribute values of the same candidate attribute of the product and the product to be compared to obtain a product-level comparison result, and the product-level comparison result can indicate the quality condition of the product and the product to be compared on the at least one candidate attribute;
and the first generation unit is used for generating and outputting reply information aiming at the inquiry information by utilizing the attribute value of the target attribute and the product-level comparison result.
The present application further provides a computer device, comprising:
a communication interface;
a memory for storing a program for implementing the question-answering information processing method as described above;
and the processor is used for loading and executing the program stored in the memory and realizing the steps of the question answering information processing method.
Therefore, compared with the prior art, the application provides a question and answer information processing method, a question and answer information processing device and computer equipment, after the computer equipment acquires inquiry information of a product, target attributes of the product, namely product attributes which are most concerned by a user, can be extracted from the inquiry information, then the target attributes are used for inquiring an attribute relation diagram of the product to obtain at least one candidate attribute of the product, namely other attributes with high correlation with the target attributes of the product, and then reply information is generated for the user to view based on the target attributes which the user wants to know and the attribute values of the candidate attributes. Therefore, the reply information generated by the application can lead the contained candidate attributes to be different along with the different target attributes contained in the inquiry information, thereby realizing the targeted reply to the inquiry content of the user and improving the accuracy and reliability of the reply information.
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 description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1a shows a schematic diagram of a system architecture for implementing a method for processing question answering information according to an embodiment of the present application;
fig. 1b is a schematic diagram of a system architecture for implementing a method for processing question answering information according to an embodiment of the present application;
fig. 2 is a schematic flowchart illustrating a method for processing question and answer information according to an embodiment of the present application;
FIG. 3 illustrates an attribute relationship diagram provided by an embodiment of the present application;
fig. 4 is a schematic flow chart illustrating another method for processing question and answer information according to an embodiment of the present application;
fig. 5 is a schematic flowchart illustrating a further method for processing question and answer information according to an embodiment of the present application;
fig. 6 is a schematic flow chart illustrating a method for acquiring products to be compared in a question answering information processing method provided in an embodiment of the present application;
fig. 7 is a schematic flowchart illustrating an implementation method for constructing an attribute relationship diagram of a product in a question-answering information processing method according to an embodiment of the present application;
fig. 8 is a scene schematic diagram illustrating a method for processing question answering information according to an embodiment of the present application;
fig. 9 is a schematic structural diagram illustrating a question answering information processing apparatus according to an embodiment of the present application;
fig. 10 is a schematic structural diagram illustrating another question answering information processing apparatus according to an embodiment of the present application;
fig. 11 is a schematic structural diagram illustrating still another question answering information processing apparatus according to an embodiment of the present application;
fig. 12 shows a hardware structure diagram of a computer device according to an embodiment of the present application.
Detailed Description
The inventor finds that: in the product attributes in the feedback reply information aiming at different inquiry information of the product, the existing intelligent customer service system is often the key attributes of the product or a plurality of fixed attributes which are inquired most often except the target attributes which are actually inquired, and the correlation between the attributes and the target attributes is poor, so that a user cannot further know the product information through the related attributes, such as the advantages of the product under a certain attribute, the grade of the product compared with the similar products in the industry, and the like.
In contrast, some application platforms propose a scheme for comparing attribute values of multiple similar products, that is, attribute values of most attributes (specifically, all attributes) of multiple products of the same type and different models are listed for comparison, and although the attributes that the user wants to know are shown to the user, the user includes many attributes that the user does not want to know, and needs to browse and look up one by one, which is relatively redundant, resulting in poor user experience.
In order to improve the above problem, the inventor of the present application proposes that a target attribute included in query information provided by different users, that is, a product attribute that a user most wants to know, is obtained, and then, response information is generated based on the target attribute and an attribute value of the at least one candidate attribute, so that the response information includes the target attribute that the user wants to know and a related attribute thereof, and the user does not need to include an attribute that is not related to the target attribute, that is, a product attribute that the user wants to know, that is, most of attributes (specifically, all attributes) of a listed product are not needed, and then the user refers to the response information one by one, thereby reducing the workload of the user, enabling the user to know the product information more quickly and accurately, and improving the user experience.
Moreover, under the condition that the target attributes contained in the inquiry information are different, the obtained at least one candidate attribute is different, so that the generated reply information is different, compared with the prior art for replying and presetting the attribute values of a plurality of fixed product attributes, the reply information obtained based on the scheme provided by the inventor is flexible and accurate in content, can reply the inquiry of the user in a targeted manner, and meets the inquiry requirements of different users.
Furthermore, the inquiry product and the like products can be compared in the aspects of the target attribute and the at least one candidate attribute, so that the advantages of the inquiry product in the industry and the grade of the same product can be known, the effect of recommending the product can be achieved, the user can further know the advantages of the product and the industry, and the user experience can be further improved.
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.
Referring to fig. 1a, for a system architecture for implementing a method for processing question answering information according to an embodiment of the present application, the system may include a terminal 11 and a computer device 12, where:
the terminal 11 may be an electronic device such as a mobile phone, a computer, an industrial personal computer, and the like, and a user may log in an application platform providing product information using a client in the terminal 11 and inquire the product information on the application platform. The client may be an application installed for the application platform, that is, a professional application, or an application such as a browser, so that a user logs in the application platform through a web page, and the type of the client is not limited in the present application.
In practical application, a user logs in an application platform by using a client, and can output a client interaction interface on a display screen of the terminal 11, the client interaction interface can provide various information input modes, such as inputting information by using a keyboard, inputting voice information, selecting input information by using a mouse, and the like, the user can input inquiry information according to actual needs, and the client interaction interface and the information input mode thereof are not limited by the application.
It can be seen that, after a user logs in a certain application platform, inquiry information of a product can be input on a client interaction interface and sent to computer equipment, and the computer equipment obtains reply information aiming at the inquiry information according to a question-answer information processing method described in the following embodiments, and displays the reply information on the client interaction interface or other generated interfaces for the user to quickly and accurately view the product information.
The computer device 12 may be a service device for providing services for the application platform, and may specifically be composed of one or more servers. The intelligent customer service system as described above may be deployed in the computer device 12, and is configured to process query information input by a user, obtain corresponding reply information, feed back to a client sending the query information, and display the query information on a customer interaction interface of the client. With regard to the processing of the query information by the computer device, reference may be made to the following detailed description of the method embodiments.
If the client sending the inquiry information is a professional application program of the product application platform, the computer equipment can be service equipment matched with the client; if the client sending the query information is a browser, i.e. logs in the product application platform through a web page, such as the system architecture shown in fig. 1b, the system may further include a server 13 matched with the client, and the client may send the query information to the server and forward the query information to the corresponding computer device 12 through the server, but is not limited to this information transmission manner.
It should be understood that the system components for implementing the question and answer information processing method are not limited to the above terminal 11 and computer device 12, and may further include a data storage device capable of being connected to the computer device in a communication manner, and used for storing information such as attribute values of product attributes, and of course, the data storage device may also be disposed in the computer device 12, and the present application does not limit the system components for implementing the answer information processing method.
Based on the system architecture shown in fig. 1a and fig. 1b, referring to fig. 2, a flow chart of a method for processing question and answer information provided in the embodiment of the present application is schematically illustrated, and the method may be applied to a computer device in the system architecture, as shown in fig. 2, and the method may include, but is not limited to, the following steps:
step S11, acquiring inquiry information of the product;
in practical applications, a user may log in a product application platform to inquire about related information of a product, and the specific obtaining manner of the inquiry information is not limited in this embodiment.
Optionally, after the user logs in the product application platform, the query information of the product that the user wants to know, such as the size of the screen of the product a, the cruising ability of the product a, and the like, may be directly input in the query input box in the client interaction interface, that is, the user may directly input the query information including the target attribute of the product (that is, the product information that the user wants to know), but the implementation manner of how to input the query information in the query input box is not limited in this embodiment, and may be implemented by using an input device such as a keyboard, a voice module, a touch screen, and the like.
As another optional embodiment, if the current customer interactive interface shows product information or can know the corresponding product according to the context, the user can also directly ask related questions, such as what the screen size is, how much the cruising ability is, and the like; certainly, the user can also generate corresponding inquiry information by clicking or selecting a certain prompt message, and send the inquiry information to the computer device. The prompt information can be displayed in a mode of characters, images, sounds or images, and the selection of the user on the prompt information can be in a mode of checking, clicking or voice selection.
It can be seen that, for the query information obtained in step S11, the query information may be directly input by the user in the query input box, or may be generated based on a selection operation of the user on the product information, or based on a product determination mentioned in the current interface context, and the like, which may specifically be determined according to the content of the client interaction interface output by the terminal display screen, but is not limited to the several implementation manners listed herein.
Step S12, extracting the target attribute of the product from the inquiry information;
in the above analysis, the query information obtained by the computer device is generated for a certain product, where the query information includes related information of the product, such as a product attribute, and the product attribute included in the query information may be regarded as a target attribute, that is, an attribute of the product that the user wants to know most, such as a mobile phone screen size, cruising ability, and memory.
Based on this, in this embodiment, feature extraction may be performed on the obtained query information to obtain the target attribute included in the query information, and a specific adopted feature extraction method is not limited, such as a text feature extraction method, a keyword extraction and comparison method, and the like.
Step S13, using the target attribute to inquire the attribute relation chart of the product and obtain at least one candidate attribute of the product;
the attribute relationship graph may include a correlation coefficient between different attributes of the product, and the correlation coefficient represents the correlation between two corresponding attributes, and in general, the larger the correlation coefficient between two attributes is, the higher the correlation between the two attributes is.
If the attribute relationship graph G of the product is defined as G ═ E, R >, E ═ E1, E2, …, em }, R ═ { R1, R2, …, rn }, m, n is a positive integer, each element in E may represent an attribute of the product, each element in R may represent a correlation coefficient between corresponding two attributes in the attribute relationship graph, for example, R1 may represent a correlation coefficient between E1 and E2, R2 may represent a correlation coefficient between E1 and E3, R may include a correlation coefficient between any two elements in E, or may include only a correlation coefficient between some elements in E.
Taking the product as a mobile phone as an example, referring to the attribute relationship diagram of the mobile phone shown in fig. 3, the elements in E may include screen size, battery capacity, battery life, charging parameters, body color, camera pixels, and the like, and the values 1, 2, 3, and the like in fig. 3 may represent the correlation coefficient between the two attributes of the connection line where the two attributes are located, and the larger the correlation coefficient is, the more the two attributes are correlated. It should be noted that fig. 3 is only used to schematically illustrate the attribute relationship diagram of the product, the attribute of the mobile phone and the correlation coefficient between the attributes, and is not limited to the contents shown in fig. 3.
Optionally, for the attribute relationship diagram of the product, the attribute relationship diagram may be constructed by using product description information of a large number of similar products and by adopting a keyword co-occurrence manner, and a specific construction method is not limited. The product description information may be generated by a developer when the product is released, or may be input by a product user, and the generation method of the product description information is not limited in the present application.
In addition, in practical application, the product description information of the product and its similar products may be obtained from the product application platform of the product, or may be crawled from other application platforms.
Based on the above description of the attribute relationship diagram of the product, the attribute relationship diagram can indicate the correlation between the attributes of the product, so that after the target attribute of the product that the user wants to know most is obtained, the attribute relationship diagram of the product can be directly queried, and from the adjacent attributes (i.e. the attributes having direct correlation, such as the attributes directly connected to the target attribute in fig. 3) with the target attribute, the adjacent attributes having a certain correlation with the target attribute are selected as candidate attributes, i.e. other attributes that the user may be interested in to know.
Optionally, in the application, after determining a plurality of adjacent attributes of the target attribute in the attribute relationship diagram of the product, a correlation coefficient between the target attribute and each adjacent attribute may be obtained, and then at least one adjacent attribute is selected as a candidate attribute according to a descending order of the correlation coefficient, but the application is not limited to this candidate attribute obtaining method.
Step S14, generating and outputting reply information for the query information based on the attribute value of the target attribute and the attribute value corresponding to the at least one candidate attribute.
Optionally, in combination with the above description, the target attribute and the at least one candidate attribute of the product are the product attributes that the user wants to know, and in the present application, the response information for the query information may be composed directly from the attribute value of the target attribute and the attribute value corresponding to the at least one candidate attribute, so that the user can know the product information that the user wants to know at a glance after seeing the response information, and compared with the attribute values of a large number of attributes (which may be all attributes) of listed products, the user screens the attribute values that the user wants to see from the attribute values, thereby greatly reducing the workload of the user and improving the accuracy of the response information.
As another optional embodiment, the present application may further utilize the target attribute of the product and the attribute value of the at least one candidate attribute to obtain the quality condition of the product in the same type of product in the industry where the product is located, and then form the reply information for the query information according to the obtained quality condition, the target attribute of the product and the attribute value of the at least one candidate attribute, so that the user can also know the advantages of the product in the industry and effectively improve the user experience when knowing the target attribute that the user wants to know and the attribute values of the related attributes thereof.
It should be noted that, the specific generation manner of the reply information and the content contained in the reply information are not limited to the above listed alternative embodiments, and may be adjusted according to actual needs, and the reply information is not listed in the present application.
In addition, for the obtained reply information, the knowledge card containing the reply information can be generated according to a preset format, sent to the user client and presented on a client interaction interface output by the client, so that the reply information can be clearly and orderly displayed, a user can conveniently and accurately select certain product information to check, and the generation method of the knowledge card is not limited by the application.
To sum up, according to the above manner, the present embodiment determines the product attribute that the user most wants to know (i.e. the target attribute), and at least one other product attribute that is most related to the product attribute, i.e. at least one candidate attribute, and then generates the reply information by using the specific attribute values of the determined product attributes, so that the reply information fed back to the user contains the attribute value of the target attribute that the user most wants to know, and also contains the attribute values of other product attributes related to the target attribute, i.e. other product attributes that the user should want to know, and the other product attributes will change with the change of the target attribute queried by the user, and are no longer the fixed key attribute or the product attribute that is most frequently queried, so that the flexibility of the reply information is improved, and the request requirements of the user are better met, and because the reply information does not contain the product attribute that is not related to the target attribute, the user does not need to filter the product attributes expected to be known from the obtained reply information, the workload of the user is reduced, the reply information output by the embodiment can help the user to intuitively and accurately know the product information which the user wants to know most, and the accuracy and reliability of the generated reply information are greatly improved.
Referring to fig. 4, a schematic flow chart of another method for processing question and answer information provided in the embodiment of the present application may include, but is not limited to, the following steps:
step S21, acquiring inquiry information of the product;
step S22, extracting the target attribute of the product from the inquiry information;
regarding the implementation process of step S21 and step S22, reference may be made to the description of the corresponding parts of step S11 and step S12 of the above-described embodiments.
Step S23, inquiring the attribute relation graph of the product, determining the adjacent attribute of the target attribute, and obtaining the correlation coefficient between the target attribute and the adjacent attribute;
for the description of the attribute relationship diagram of the product, reference may be made to the description of the corresponding part of the above embodiment, which includes a plurality of attributes of the product and a correlation coefficient between any two attributes. Therefore, after determining the target attribute of the product, the queried attribute relationship diagram may be queried to determine at least one adjacent attribute of the target attribute, and a correlation coefficient between the target attribute and each adjacent attribute, where the correlation coefficient represents a degree of correlation between the target attribute and the corresponding adjacent attribute.
Taking the attribute relationship diagram shown in fig. 3 as an example, the target attribute may be battery life, and its neighboring attributes include battery capacity, screen size, body color, charging parameters, and camera pixels; if the target attribute is screen size, its neighboring attributes may include battery capacity and battery life; if the target attribute is a charging parameter, the neighboring attributes may include battery life, etc. It can be seen that, for different target attributes of a product, the number and content of adjacent attributes may be different, and the number and content may be determined specifically based on a pre-constructed attribute relationship diagram of the product, and are not limited to the content exemplified herein.
Optionally, the application may further update the attribute relationship diagram of the product, for example, after the industry concerns that the product attribute changes, the content of the product description information may be affected, so the application may obtain the changed product description information, and update the attribute relationship diagram of the product by using the changed product description information, for example, update the attribute content included in the attribute relationship diagram, the correlation coefficient value between two attributes, and the like. After the query information is acquired, the updated attribute relationship graph can be used for querying the adjacent attributes of the target attribute queried by the user and the correlation coefficient between the target attribute and each adjacent attribute.
Step S24, selecting at least one adjacent attribute corresponding to the larger correlation coefficient as a candidate attribute;
in practical application of this embodiment, in the case of acquiring a plurality of candidate attributes, corresponding candidate attributes may be sorted in an order from a large correlation coefficient to a small correlation coefficient, and a certain number of adjacent attributes ranked earlier may be selected as candidate attributes, but the method is not limited to this candidate attribute acquisition method.
Step S25, acquiring a product to be compared for the product based on the attribute value of the target attribute;
in order to enable the user to know the advantages of the product queried by the user in the industry, especially the advantages of the product attribute that the user wants to know, the present embodiment may obtain, based on the attribute value of the product attribute that the user most wants to know, other products that the user wants to effectively compare with the product queried by the user, and mark the other products as products to be compared, that is, similar products that are comparable to the product queried by the user in terms of the target attribute, and the present application does not limit the specific implementation manner of step S25.
Step S26, comparing the product with the attribute value of the same candidate attribute of the product to be compared to obtain a product-level comparison result;
it can be seen that, in the embodiment, in consideration of the target attribute of the product, at least one product to be compared, which is comparable to the product, is screened from a plurality of similar products of the product, and then, in consideration of each candidate attribute, the product and the screened product to be compared are compared, so as to determine the quality of the product in terms of the target attribute and each candidate attribute in the industry, specifically, as a result of comparison between the product and the product to be compared in terms of the target attribute and the candidate attribute.
Therefore, the product-level comparison result obtained in this embodiment can indicate the quality of the target product and the product to be compared in at least one candidate attribute, such as the percentage of the target attribute and/or the candidate attribute of the product being superior or the quality score relative to the product to be compared, the percentage of the target attribute and/or the candidate attribute of the product being superior or the quality score relative to the corresponding attribute value of the same type of product in the industry, and the like.
Step S27, using the attribute value of the target attribute and the product-level comparison result, generates and outputs reply information for the inquiry information.
It can be seen that the reply information generated by the embodiment includes the attribute value of the product attribute that the user wants to know most, i.e., the attribute value of the target attribute, and also includes the product-level comparison result of the product, so that the user can accurately know the advantages of the product in the same kind of products in the industry, and the effect of recommending the product is achieved.
The product-level comparison result may include an attribute value of at least one candidate attribute of the product and the product to be compared, and product quality information obtained based on the comparison of the attribute values of the candidate attributes, such as how much the candidate attribute of the product is superior to a percentage of similar products, and therefore, the user can also intuitively know other attributes (i.e., candidate attributes) of the product related to the target attribute by looking up the reply information, so as to further know the product information of the product accordingly.
Referring to fig. 5, a schematic flow chart of another method for processing question and answer information provided in the embodiment of the present application, where the embodiment may be a specific implementation manner of how to obtain a product to be compared based on an attribute value of a target attribute for the above optional embodiment, but is not limited to this implementation manner, as shown in fig. 5, the method may include, but is not limited to, the following steps:
step S31, acquiring inquiry information of the product;
step S32, extracting the target attribute of the product from the inquiry information;
step S33, using the target attribute to inquire the attribute relation chart of the product and obtain at least one candidate attribute of the product;
regarding the implementation of step S31-step S33, reference may be made to the description of the corresponding portions of step S11-step S13 in the above-mentioned embodiments, and the specific implementation manner of step S33 may adopt the contents described in step S23 and step S24 in the above-mentioned embodiments, but is not limited to this implementation manner.
Step S34, acquiring a reference attribute value of the target attribute of the industry where the product is located;
the reference attribute value may be a standard accepted in the industry for evaluating the quality of the attribute of the product, and the reference attribute value of the corresponding attribute in the industry of the product may be calculated by obtaining the attribute values of different attributes of the same product in the industry of the product and further using the attribute values of different attributes. Specifically, for the similar products, the attribute values of the products are collected, the data sets corresponding to the attributes are established according to the collected attribute values of the attributes, and the parameter attribute values of the corresponding data are counted according to the attribute values included in each data set.
In practical applications, a specific method for counting the reference attribute value may be determined according to specific content of the reference attribute value, for example, the reference attribute value may be an average attribute value, which may also be referred to as a standard attribute value, that is, the attribute value of the corresponding attribute of the product reaches the labeled attribute value, and the attribute of the product may be considered to reach an average level in the industry.
Optionally, the reference attribute value may further include an optimal attribute value, that is, an attribute value corresponding to the industry considers that the corresponding attribute of the product is optimal.
Based on the above analysis, the present embodiment may obtain the reference attribute value of the target attribute of the similar product in the industry where the product is located, such as the standard attribute value, the optimal attribute value, and the like of the target attribute, in the manner described above.
Step S35, comparing the attribute value of the target attribute of the product with the reference attribute value to obtain a target attribute comparison result;
since the target attribute is the product attribute that the user wants to know most, the present embodiment can know the target attribute of the product by comparing the attribute value of the target attribute with the reference attribute value, and the quality level of the similar product, that is, the target attribute comparison result can indicate the quality condition of the product and other similar products in the target attribute, that is, the quality level of the target attribute of the product in the industry where the product is located.
Optionally, the target attribute comparison result may include an attribute difference between an attribute value of a target attribute of the product and the reference attribute value, or may include a goodness score obtained based on the attribute difference, where the goodness score may be a percentage, a score, and the like, and in this embodiment, the goodness score represents a goodness condition of the product attribute in a similar product, and in a general case, the greater the goodness score, the better the corresponding attribute of the product is. It should be noted that the content included in the target attribute comparison result is not limited to the content listed herein, and may be determined according to actual needs.
Step S36, based on the target attribute comparison result, obtaining the product to be compared corresponding to the reference attribute value;
the product to be compared determined in this embodiment may be one product or multiple products, that is, at least one type of product, and in combination with the above analysis, it may be regarded as a similar product that is in valuable comparison with the product in terms of the target attribute of the product.
Because the target attribute comparison result can indicate the quality of the product and other similar products in the target attribute, the embodiment can screen a plurality of products which are most valuable compared with the product from a large number of similar products as products to be compared.
Optionally, referring to fig. 6, if the reference attribute of the target attribute includes the optimal attribute value and the standard attribute value of the target attribute in the industry where the product is located, the specific implementation method of the step S35 and the step S36 may be, but is not limited to, the following steps:
step A1, calculating a first difference value between the attribute value of the target attribute of the product and the optimal attribute value of the target attribute;
in this embodiment, a difference operation may be directly adopted to implement step a1, that is, if the first difference is equal to the attribute value of the target attribute — the optimal attribute value of the target attribute, it indicates that the target attribute of the product is at the top position of the same product in the industry if the first difference is a positive number; if the first difference is a negative number, it indicates that the target attribute of the product does not reach the top position of the same type of product in the industry, and the position of the target attribute of the product in the same type of product can be further determined based on the specific numerical value of the first difference.
Step A2, judging whether the absolute value of the first difference is smaller than a first threshold value, if so, entering step A3, and if not, executing step A4;
the embodiment can determine which similar products to screen the products to be compared from by judging the attribute value of the target attribute of the product and the difference between the attribute value of the target attribute and the optimal attribute value of the target attribute in the industry where the product is located. Specifically, if the absolute value of the first difference is smaller than the first threshold, the attribute value of the target attribute of the product may be considered to have a smaller difference from the optimal attribute value of the target attribute in the industry where the product is located, and the target attribute of the product may be considered to be located at a higher position of a similar product.
On the contrary, if the absolute value of the first difference is greater than the first threshold, it may be considered that the difference between the attribute value of the target attribute of the product and the optimal attribute value of the target attribute in the industry where the product is located is large, that is, the position of the target attribute of the product in the similar product is not high, and it may be further determined whether the target attribute is located at a middle position in the similar product, that is, the winning level is general, so as to obtain another product, as a product to be compared, whose position is not much different from the position of the product in the similar product.
Step A3, generating a target attribute comparison result by using the absolute value of the first difference, and acquiring a product to be compared with the optimal attribute value of the target attribute;
as described above, in this case, the target attribute of the product is located at a higher position of the similar product, and a plurality of products to be compared can be screened from the similar product having the optimal attribute value of the target attribute. Meanwhile, a target attribute comparison result can be generated based on the absolute value of the first difference, so that the quality of the target attribute of the product in the similar product can be known more intuitively.
Step A4, calculating a second difference between the attribute value of the target attribute of the product and the standard attribute value of the target attribute;
and step A5, generating a target attribute comparison result by using the absolute value of the second difference, and acquiring a product to be compared with the standard attribute value of the target attribute.
Therefore, the target attribute comparison result generated under the condition can indicate the quality condition of the target attribute of the product and the like products at the industry average position, and the obtained products to be compared can be the like products at the industry average position. Step S37, comparing the product with the attribute value of the same candidate attribute of the product to be compared to obtain a product-level comparison result;
as analyzed above, in the case where the target attribute of the product is less dominant in the similar products, the candidate attributes of the product at the average position of the product and the target attribute in the industry may be further compared to determine whether the product is dominant in the candidate attributes. Therefore, the embodiment may determine the product to be compared corresponding to the standard attribute value of the target attribute, compare the product with the attribute value of the same candidate attribute of the product to be compared, and determine whether the product has advantages, specifically what advantages, etc. compared with the candidate attribute of the product to be compared.
It should be noted that the product to be compared determined by any method may be one or more products, and the specific product model is not limited.
Optionally, the product-level comparison result may include an attribute value of a candidate attribute of the product and a product to be compared, and a comparison result of the attribute values, or a goodness score of the product obtained from the comparison result with respect to the product to be compared, or a goodness score of a similar product in which the product is at an average position with respect to the industry candidate attribute, and the like, and the content of the product-level comparison result is not limited in the present application.
Step S38, determining a target candidate attribute of at least one candidate attribute according to the product-level comparison result;
in this embodiment, for a product provider, the product application platform is expected to promote its product, so that more users select the product, and therefore, what is often included in the reply information fed back to the users by the computer device is content favorable for product promotion.
Step S39, obtaining reply information aiming at the inquiry information based on the attribute value of the target attribute and the attribute value of the target candidate attribute;
in this embodiment, the obtained attribute value of the target attribute and the attribute value of the target candidate attribute, and the product level comparison result corresponding to the target candidate attribute and/or the target attribute comparison result may be directly used to obtain the reply information for the query information. Therefore, the generated reply information at least includes the attribute value of the target attribute of the product and the attribute value of the target candidate attribute, and on this basis, the generated reply information may also include the attribute value of the target attribute of the product to be compared and the attribute value of the target candidate attribute, and the target attribute comparison result and/or the product-level comparison result, etc., may configure the information type included in the reply information that needs to be generated according to the actual needs, and is not limited to the contents listed in this application.
In step S310, a knowledge card of the product is produced and output by using the reply information.
The method for manufacturing the knowledge card is not limited, after the reply information aiming at the inquiry information is obtained, the corresponding knowledge card can be manufactured according to the information type contained in the reply information and sent to the user client, and the knowledge card is displayed through the client interaction interface of the user client. That is to say, the application can adopt the form of the knowledge card to realize the display of the obtained reply information, and the user can visually see the information type contained in the reply information and select to view the product information displayed by the knowledge card according to the requirement, such as the target attribute, the attribute value of the candidate attribute, and the like, so that the user can be helped to quickly, accurately and deeply know the advantages of the product in the industry where the product is located.
Moreover, the information contained in the knowledge card generated by the embodiment is not the fixed and unchangeable attribute values of the product attributes, but the attribute values of the related attributes obtained by inquiring the target attribute by the user and the positions of the product in the similar products under the target attribute and the candidate attribute enrich the content of the reply information, improve the accuracy and flexibility of the reply information, help the user to obtain more, more accurate and more meaningful information, increase the good feeling of the user to the product, and achieve the effect of recommending the product.
Referring to fig. 7, a flowchart of an implementation method for constructing an attribute relationship diagram of a product in a question and answer information processing method provided in an embodiment of the present application is provided, but is not limited to the construction method provided in this embodiment, and as shown in fig. 7, the method may include:
step S41, acquiring product description information of the industry where the product is located;
regarding the implementation of step S41, reference may be made to the description of the corresponding parts of the above embodiments, and the present application does not limit the source of the product description information and the obtaining manner thereof.
Step S42, extracting the attributes contained in the product description information;
since the product description information includes two or more attributes, it can be stated that there is a correlation between the attributes, and for the product description information including one attribute, the correlation between the attributes of the product cannot be known, so that the embodiment may determine the number of the attributes of the product included in each piece of product description information by executing step S42.
Step S43, acquiring a plurality of preset attributes of the product;
the preset attributes of the product can be key attributes of the product, attributes frequently inquired by a user at the current stage, and the like, and can also comprise most attributes of the product, even all attributes, according to needs.
In practical applications, when a user reviews a product, the published product description information often includes one or more preset attributes, and as can be seen, the attribute extracted in step S42 may be the preset attribute of the product.
Step S44, establishing an incidence relation between corresponding preset attributes by using at least two attributes contained in the product description information, and determining a correlation coefficient between the corresponding preset attributes;
the method and the device can utilize at least two attributes contained in the product description information to construct the attribute relation graph of the product. Specifically, product description information including attributes of at least two products is screened from a large amount of acquired product description information, then, an association relation between corresponding preset attributes is established by using the attributes included in the screened product description information, and a correlation coefficient between the corresponding preset attributes is determined.
In combination with the attribute relationship diagram shown in fig. 3, if a certain piece of product description information includes two attributes, namely, the battery capacity and the screen size, it is indicated that the two attributes have a certain correlation, and the correlation between the two attributes can be established, and 1 is added to the correlation coefficient between the two attributes. In this way, the attributes included in the screened product description information are processed, and it can be determined which preset attributes have correlation among the preset attributes of the product at the current stage, and how much the correlation degree among the preset attributes is.
It should be noted that the method for determining the correlation between the preset attributes of the product is not limited to the manner described in the present embodiment.
Step S45, constructing an attribute relationship diagram of the product according to the relationship between the plurality of preset attributes and the corresponding correlation coefficients.
Therefore, in the question-answering information processing process described in the above embodiments, after determining the target attribute of the product queried by the user, querying the attribute relationship diagram of the product can quickly and accurately obtain the relevant attribute of the target attribute so as to select at least one candidate attribute from the target attribute, generate reply information for the query information based on the at least one candidate attribute and the attribute value of the target attribute, meet the query requirement of the current user, and enable the user to know the product information more deeply through the content of the reply information.
In order to more clearly understand the method for processing question and answer information, the present application takes a scenario in which a user uses an intelligent customer service system to inquire x mobile phone information as an example, and with reference to a scenario diagram shown in fig. 8, the user uses a client on a terminal to enter the intelligent customer service system, and inputs inquiry information of "how long the battery life of x mobile phone is", so that after computer equipment where the intelligent customer service system is located obtains the inquiry information, the mobile phone attribute contained in the inquiry information, namely "battery life", is extracted, and then, a pre-constructed attribute relationship diagram of the mobile phone is queried to obtain mobile phone attributes related to the battery life, taking the attribute relationship diagram shown in fig. 3 as an example, the related attributes of the battery life include: the correlation coefficients of the battery capacity, the screen size, the charging parameters, the camera pixels, the body color and the like with the battery life are 3, 2, 1 and 1 in sequence. According to the obtained correlation coefficient, a plurality of correlation attributes with high correlation degree can be selected as candidate attributes, three mobile phone attributes including battery capacity, screen size and charging parameters are selected as the candidate attributes in the embodiment, and most attributes of the mobile phone are not required to be obtained.
Then, the computer equipment can also obtain a plurality of mobile phones to be compared by using the attribute value of the battery life, specifically, the battery life value of the x mobile phone can be compared with the optimal value of the battery life in the mobile phone industry, and if the difference is not large, a plurality of mobile phones with the optimal value of the battery life are used as the mobile phones to be compared; and if the difference is larger, taking the plurality of mobile phones which acquire the standard value of the service life of the battery as the mobile phones to be compared.
Based on this, after comparing the attribute values of the candidate attributes of the x mobile phone and each mobile phone to be compared, the quality of each candidate attribute of the x mobile phone in the mobile phone industry is further known, namely the product-level comparison result, the candidate attribute with the superiority of the x mobile phone can be screened as the target candidate attribute, such as battery capacity and screen size, finally, reply information is generated by using the specific attribute values of the battery life, the battery capacity and the screen size of the x mobile phone, the battery life comparison result and the product-level comparison result, and is fed back to the display screen of the user terminal for display in the form of a knowledge card, the method and the device enable a user to know the advantages of the x mobile phone in the mobile phone industry in the aspects of the specific attribute values of the battery life, the battery capacity and the screen size of the x mobile phone which the user wants to know, and help the user to effectively select the required mobile phone.
The attribute relationship diagram of the mobile phone can be obtained through the crawled mobile phone description information, and the specific construction process can refer to the description of the corresponding part of the embodiment.
Therefore, compared with the prior art, aiming at the inquiry information, the reply information fed back by the intelligent customer service system is usually a battery life value and attributes which are not required by the user, such as fixed mobile phone camera pixel size, memory capacity, body color, system type and the like.
Compared with the mode of listing the attribute values of most attributes of the mobile phone, the method and the device do not need a user to spend a large amount of time, the attribute value of the required attribute is searched from the reply information, and the workload of the user is reduced.
Referring to fig. 9, a schematic structural diagram of a question answering information processing apparatus provided in an embodiment of the present application, where the apparatus may be applied to a computer device, as shown in fig. 9, the apparatus may include:
a first obtaining module 21, configured to obtain inquiry information of a product, and extract a target attribute of the product from the inquiry information;
the query module 22 is configured to query an attribute relationship graph of the product by using the target attribute to obtain at least one candidate attribute of the product, where the attribute relationship graph includes correlation coefficients between different attributes of the product;
optionally, the query module 22 may include:
the first query unit is used for querying the attribute relation graph of the product, determining the adjacent attribute of the target attribute and acquiring the correlation coefficient between the target attribute and the adjacent attribute;
and the first selection unit is used for selecting at least one adjacent attribute corresponding to the larger correlation coefficient as a candidate attribute.
And the reply information generating module 23 is configured to generate and output reply information for the query information based on the attribute value of the target attribute and the attribute value corresponding to the at least one candidate attribute.
Therefore, the reply information output by the application can not only enable the user to know the attribute value of the product attribute which the user wants to know most, but also can know the attribute value of the related product attribute, and helps the user to further know the product information. In addition, the reply information obtained by the embodiment does not include the attribute values of most attributes of the product, but includes the attribute values of the target attribute and the related attribute (i.e., the candidate attribute) that the user wants to know, so that the user can directly view the product information (such as the attribute values) that the user wants to know, the user does not need to search the attribute values that the user wants to know from a large number of listed attributes, the workload of the user is reduced, and the accuracy of the reply information is improved.
Optionally, as shown in fig. 10, the reply information generating module 23 may include:
a first obtaining unit 231, configured to obtain a product to be compared for the product based on an attribute value of a target attribute;
in this application, the first obtaining unit 231 may include:
the parameter attribute value acquisition unit is used for acquiring a reference attribute value of the target attribute of the industry where the product is located;
optionally, in this embodiment, in order to obtain a reference attribute value of the target attribute, the apparatus may further include:
the second acquisition module is used for acquiring attribute values of different attributes of the same product in the industry of the product;
and the reference attribute value calculation module is used for calculating the reference attribute value of the corresponding attribute in the industry of the product by using the attribute values of the different attributes.
A target attribute comparison result obtaining unit, configured to compare an attribute value of the target attribute of the product with the reference attribute value, to obtain a target attribute comparison result;
and the to-be-compared product obtaining unit is used for obtaining the to-be-compared product corresponding to the reference attribute value based on the target attribute comparison result.
In the application, the obtained products to be compared can be one or more products of the same type, and the models of different products are different.
In addition, with regard to how the first obtaining unit 231 obtains the implementation process of the product to be compared, reference may be made to the description of the corresponding parts of the above-described method embodiments.
A first comparing unit 232, configured to compare attribute values of the same candidate attribute of the product and the product to be compared, so as to obtain a product-level comparison result;
wherein, the product-level comparison result can indicate the quality of the product and the product to be compared on the at least one candidate attribute, and the content of the product-level comparison result is not limited by the application.
A first generating unit 233 for generating and outputting reply information for the query information using the attribute value of the target attribute and the product-level comparison result.
Alternatively, the first generating unit 233 may include:
a target candidate attribute determining unit, configured to determine a target candidate attribute of the at least one candidate attribute according to the product-level comparison result, where the target candidate attribute is a candidate attribute of the product superior to the product to be compared;
a reply information obtaining unit, configured to obtain reply information for the query information based on the attribute value of the target attribute and the attribute value of the target candidate attribute;
the reply information obtaining unit may be specifically configured to obtain the reply information for the query information by using the attribute value of the target attribute, the attribute value of the target candidate attribute, the product level comparison result corresponding to the target candidate attribute, and/or the target attribute comparison result.
With regard to the generation process of the reply information to the inquiry information, the description of the corresponding part may be drawn with reference to the above-described method embodiment.
And the knowledge card making unit is used for making and outputting the knowledge card of the product by using the reply information.
Therefore, the reply information fed back to the user by the application not only comprises the target attribute which the user wants to know and the attribute value of the related attribute, but also comprises the target attribute comparison result and/or the product-level comparison result, so that the user can know the position of the product in the same product in the industry, and more intuitively know the advantages of the product relative to the same product.
Optionally, in order to improve the effect of recommending a product, the application may flexibly select an object to be compared with the product, specifically, the reference attribute value of the target attribute of the product may include an optimal attribute value and a standard attribute value of the target attribute, and the target attribute comparison result obtaining unit may include:
a first calculating subunit, configured to calculate a first difference between an attribute value of the target attribute of the product and an optimal attribute value of the target attribute;
the first generation subunit is configured to, when the absolute value of the first difference is smaller than a first threshold, generate a target attribute comparison result using the absolute value of the first difference;
correspondingly, the to-be-compared product obtaining unit is specifically configured to obtain the to-be-compared product having the optimal attribute value of the target attribute.
The second calculating subunit is used for calculating a second difference value between the attribute value of the target attribute of the product and the standard attribute value of the target attribute under the condition that the absolute value of the first difference value is not smaller than the first threshold value;
the second generation subunit is used for generating a target attribute comparison result by using the absolute value of the second difference value;
correspondingly, the to-be-compared product obtaining unit is specifically configured to obtain the to-be-compared product having the standard attribute value of the target attribute.
Optionally, in order to implement the construction of the attribute relationship diagram of the product, as shown in fig. 11, the apparatus may further include:
a third obtaining module 24, configured to obtain product description information of an industry where the product is located;
an attribute extraction module 25, configured to extract an attribute included in the product description information;
the building module 26 is configured to build an attribute relationship diagram of the product by using at least two attributes included in the product description information.
In practical applications, the building module 26 may include:
the second acquisition unit is used for acquiring a plurality of preset attributes of the product;
the relationship establishing unit is used for establishing an incidence relationship between corresponding preset attributes by using at least two attributes contained in the product description information and determining a correlation coefficient between corresponding adjacent preset attributes;
and the construction unit is used for constructing an attribute relation graph of the product according to the incidence relation among the preset attributes and the corresponding correlation coefficient.
The attribute relationship diagram of the product constructed by the present application may be updated periodically, or may be updated according to the change of the obtained product description information, and the like.
Therefore, in the embodiment, by using the updated attribute relationship diagram of the product, the obtained related attributes of the target attributes can meet the development of the product in the current stage of the industry, the accuracy of the obtained related attributes is improved, and the generated response information can further meet the query requirements of the user.
Referring to fig. 12, a schematic diagram of a hardware structure of a computer device according to an embodiment of the present disclosure is provided, where the computer device may be a server, and in an intelligent customer service application scenario, the computer device may be a server deployed with an intelligent customer service system, and in this embodiment, the computer device may include: a communication interface 31, a memory 32, and a processor 33, wherein:
the number of each of the communication interface 31, the memory 32, and the processor 33 may be at least one, and the communication interface 31, the memory 32, and the processor 33 may communicate with each other through a communication bus.
The communication interface 31 may be an interface of a wireless communication module and/or a wired communication module, such as an interface of a WIFI module, a GPRS module, a GSM module, and the like, and the type and the number of the communication interface 31 are not limited in the present application.
In practical application, the inquiry information, the product description information, the attribute value of the product attribute, and the like of the product may be acquired through the communication interface, and may also be used to implement data transmission and the like between the components of the computer device, and may be determined according to the specific communication requirement of the inquiry and answer information processing method, which is not described in detail herein.
The memory 32 may store a program that implements the above-described question-answer information processing method.
In practical applications of this embodiment, the memory 32 may also be used to store various intermediate data, acquired data, output data, and the like generated during the processing of the question and answer information, such as attribute values of product attributes, inquiry information, product description information, and the like.
Optionally, the memory may store program codes for implementing the functional modules included in the virtual device, and may specifically be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor 33 may be a central processing unit CPU, or an application Specific Integrated circuit asic (application Specific Integrated circuit), or one or more Integrated circuits configured to implement the embodiments of the present application, and the present application does not limit the composition of the processor 33.
In the present application, the processor 33 may be configured to load and execute the program stored in the memory 32 to implement the steps of the above-mentioned question and answer information processing method, and as for the steps of the question and answer information processing method, reference may be made to the description of the corresponding parts of the above-mentioned method embodiments.
In summary, after obtaining the target attribute included in the query information of the product, the computer device provided in the present application queries at least one candidate attribute related to the target attribute by using a pre-constructed attribute relationship diagram of the product, and then generates the reply information by using the target attribute and the attribute value of the candidate attribute, so that the reply information is provided for the user to view.
And the candidate attribute in the reply information can also change along with the change of the target attribute inquired by the user, and compared with the traditional method of feeding back the fixed key attribute or the attribute value of the most frequent attribute, the method realizes the targeted reply to the inquiry information of the user, improves the flexibility and the accuracy of the reply information, and is beneficial to increasing the good feeling of the user to the product.
Further, by combining the question and answer information processing method described above, the method can also obtain the reference attribute value of the target attribute of the similar product in the industry where the product is located, and feed back the comparison result of the target attribute and the product target attribute to the user, so as to help the user to know the position of the target attribute of the product in the similar product in the industry where the product is located; according to the requirement, the attribute values of the candidate attributes of the product and the like product can be compared, so that the user can know the advantages of the product on the candidate attributes relative to the like product, and particularly, under the condition that the target attribute of the product does not have obvious advantages in the like product, the user can further increase the knowledge of the product by displaying the advantages of the candidate attributes of the product.
Finally, it should be noted that, in the embodiments, relational terms such as first, second and the like may be used solely to distinguish one operation, unit or module from another operation, unit or module without necessarily requiring or implying any actual such relationship or order between such units, operations or modules. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method or system that comprises the element.
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 and the computer equipment disclosed by the embodiment correspond to the method disclosed by the embodiment, so that the description is relatively simple, and the relevant points can be referred to the method part for description.
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. A question-answer information processing method comprises
Acquiring inquiry information of a product, and extracting target attributes of the product from the inquiry information;
inquiring an attribute relation graph of the product by using the target attribute to obtain at least one candidate attribute of the product, wherein the attribute relation graph comprises correlation coefficients among different attributes of the product;
generating and outputting reply information aiming at the inquiry information based on the attribute value of the target attribute and the attribute value corresponding to the at least one candidate attribute;
generating and outputting reply information aiming at the inquiry information based on the attribute value of the target attribute and the attribute value corresponding to the at least one candidate attribute, wherein the reply information comprises:
obtaining a product to be compared for the product based on the attribute value of the target attribute;
comparing the attribute values of the same candidate attribute of the product and the product to be compared to obtain a product-level comparison result, wherein the product-level comparison result can indicate the quality of the product and the product to be compared on the at least one candidate attribute;
generating and outputting reply information aiming at the inquiry information by utilizing the attribute value of the target attribute and the product-level comparison result;
the generating and outputting reply information for the query information by using the attribute value of the target attribute and the product-level comparison result comprises:
determining a target candidate attribute in the at least one candidate attribute according to the product-level comparison result, wherein the target candidate attribute is a candidate attribute of the product superior to the product to be compared;
obtaining reply information aiming at the inquiry information based on the attribute value of the target attribute and the attribute value of the target candidate attribute;
and making and outputting a knowledge card of the product by using the reply information.
2. The method of claim 1, wherein obtaining a product to be compared for the product based on the attribute value of the target attribute comprises:
acquiring a reference attribute value of the target attribute of the industry where the product is located;
comparing the attribute value of the target attribute of the product with the reference attribute value to obtain a target attribute comparison result;
and acquiring the product to be compared corresponding to the reference attribute value based on the target attribute comparison result.
3. The method of claim 1, wherein obtaining reply information for the query information based on the attribute value of the target attribute and the attribute value of the target candidate attribute comprises:
and obtaining reply information aiming at the inquiry information by utilizing the attribute value of the target attribute, the attribute value of the target candidate attribute, a product level comparison result corresponding to the target candidate attribute and/or the target attribute comparison result.
4. The method according to claim 2, wherein the reference attribute value comprises an optimal attribute value and a standard attribute value of the target attribute of the industry in which the product is located, and the attribute value of the target attribute of the product is compared with the reference attribute value to obtain a target attribute comparison result; based on the target attribute comparison result, obtaining a product to be compared corresponding to the reference attribute value, including:
calculating a first difference value between the attribute value of the target attribute of the product and the optimal attribute value of the target attribute;
if the absolute value of the first difference is smaller than a first threshold, generating a target attribute comparison result by using the absolute value of the first difference, and acquiring a product to be compared with the optimal attribute value of the target attribute;
if the absolute value of the first difference is not smaller than the first threshold, calculating a second difference between the attribute value of the target attribute of the product and the standard attribute value of the target attribute;
and generating a target attribute comparison result by using the absolute value of the second difference, and acquiring a product to be compared with the standard attribute value of the target attribute.
5. The method of any of claims 1-4, further comprising:
acquiring product description information of the industry where the product is located;
extracting attributes contained in the product description information;
and constructing an attribute relation graph of the product by using at least two attributes contained in the product description information.
6. The method of claim 5, wherein the constructing the attribute relationship graph of the product by using at least two attributes included in the product description information comprises:
acquiring a plurality of preset attributes of the product;
establishing an incidence relation between corresponding preset attributes by using at least two attributes contained in the product description information, and determining a correlation coefficient between the corresponding preset attributes;
and constructing an attribute relation graph of the product according to the incidence relation among the preset attributes and the corresponding correlation coefficient.
7. The method according to any one of claims 1 to 4, wherein the querying an attribute relationship graph of the product by using the target attribute to obtain at least one candidate attribute of the product comprises:
inquiring an attribute relation graph of the product, determining adjacent attributes of the target attribute, and acquiring a correlation coefficient between the target attribute and the adjacent attributes;
and selecting at least one adjacent attribute corresponding to the larger correlation coefficient as a candidate attribute.
8. The method of any of claims 1-4, further comprising:
acquiring attribute values of different attributes of the same product in the industry of the product;
and calculating the reference attribute value of the corresponding attribute in the industry of the product by using the attribute values of the different attributes.
9. A question-answering information processing device comprises
The system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring inquiry information of a product and extracting a target attribute of the product from the inquiry information;
the query module is used for querying an attribute relation graph of the product by using the target attribute to obtain at least one candidate attribute of the product, wherein the attribute relation graph comprises correlation coefficients among different attributes of the product;
the reply information generation module is used for generating and outputting reply information aiming at the inquiry information based on the attribute value of the target attribute and the attribute value corresponding to the at least one candidate attribute;
the reply information generation module includes:
a first obtaining unit configured to obtain a product to be compared for the product based on an attribute value of the target attribute;
the first comparison unit is used for comparing the attribute values of the same candidate attribute of the product and the product to be compared to obtain a product-level comparison result, and the product-level comparison result can indicate the quality condition of the product and the product to be compared on the at least one candidate attribute;
a first generating unit, configured to generate and output reply information for the query information using the attribute value of the target attribute and the product-level comparison result;
the generating and outputting reply information for the query information by using the attribute value of the target attribute and the product-level comparison result comprises:
determining a target candidate attribute in the at least one candidate attribute according to the product-level comparison result, wherein the target candidate attribute is a candidate attribute of the product superior to the product to be compared;
obtaining reply information aiming at the inquiry information based on the attribute value of the target attribute and the attribute value of the target candidate attribute;
and making and outputting a knowledge card of the product by using the reply information.
10. A computer device, comprising:
a communication interface;
a memory for storing a program for implementing the question-answer information processing method according to any one of claims 1 to 8;
a processor for loading and executing the program stored in the memory to realize the steps of the question-answering information processing method according to any one of claims 1 to 8.
CN201910188483.5A 2019-03-13 2019-03-13 Question and answer information processing method and device and computer equipment Active CN109934631B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910188483.5A CN109934631B (en) 2019-03-13 2019-03-13 Question and answer information processing method and device and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910188483.5A CN109934631B (en) 2019-03-13 2019-03-13 Question and answer information processing method and device and computer equipment

Publications (2)

Publication Number Publication Date
CN109934631A CN109934631A (en) 2019-06-25
CN109934631B true CN109934631B (en) 2022-03-25

Family

ID=66987080

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910188483.5A Active CN109934631B (en) 2019-03-13 2019-03-13 Question and answer information processing method and device and computer equipment

Country Status (1)

Country Link
CN (1) CN109934631B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110287304B (en) * 2019-06-30 2021-11-16 联想(北京)有限公司 Question and answer information processing method and device and computer equipment
CN110912939A (en) * 2019-12-24 2020-03-24 北京每日优鲜电子商务有限公司 Cloud customer service distribution method and device, server and storage medium
CN111143540B (en) * 2020-04-03 2020-07-21 腾讯科技（深圳）有限公司 Intelligent question and answer method, device, equipment and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101295396A (en) * 2008-06-19 2008-10-29 腾讯科技（深圳）有限公司 Electronic commerce platform and its commercial articles attribute comparison method
US20140074851A1 (en) * 2012-09-13 2014-03-13 Alibaba Group Holding Limited Dynamic data acquisition method and system
CN104965839A (en) * 2014-09-25 2015-10-07 腾讯科技（深圳）有限公司 Similar information searching method and apparatus
CN106033431A (en) * 2015-03-12 2016-10-19 阿里巴巴集团控股有限公司 A method and a server for product information processing

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103049433B (en) * 2012-12-11 2015-10-28 微梦创科网络科技（中国）有限公司 The method of automatic question-answering method, automatically request-answering system and structure question and answer case library
CN108073702A (en) * 2017-12-14 2018-05-25 北京木业邦科技有限公司 Wood products recommend method, apparatus and computer readable storage medium
CN108038730A (en) * 2017-12-22 2018-05-15 联想(北京)有限公司 Product similarity determination methods, device and server cluster

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101295396A (en) * 2008-06-19 2008-10-29 腾讯科技（深圳）有限公司 Electronic commerce platform and its commercial articles attribute comparison method
US20140074851A1 (en) * 2012-09-13 2014-03-13 Alibaba Group Holding Limited Dynamic data acquisition method and system
CN104965839A (en) * 2014-09-25 2015-10-07 腾讯科技（深圳）有限公司 Similar information searching method and apparatus
CN106033431A (en) * 2015-03-12 2016-10-19 阿里巴巴集团控股有限公司 A method and a server for product information processing

Also Published As

Publication number Publication date
CN109934631A (en) 2019-06-25

Similar Documents

Publication Publication Date Title
US11061966B2 (en) Method for processing fusion data and information recommendation system
US20210390146A1 (en) Search Engine
CN109934631B (en) Question and answer information processing method and device and computer equipment
CN102073699B (en) For improving the method for Search Results, device and equipment based on user behavior
CN109873745B (en) Communication control method, communication control device and storage medium
TWI421714B (en) Recommended information generation device and recommendation information generation method
US20140136524A1 (en) Method And System For Displaying Commodity Search Results
CN110807045A (en) Data display method, device, equipment and computer readable storage medium
CN106470110B (en) Method and device for sending messages to multiple users in user list in group mode
CN102449626A (en) Open search assist
CN106980703A (en) For the method and device of group's search, electronic equipment, computer-readable medium
US20220261591A1 (en) Data processing method and apparatus
US20160165048A1 (en) Methods and systems for automated business dialing
CN109086158B (en) Abnormal cause analysis method and device and server
CN107798012B (en) Reading resource comment pushing method and system
CN105096023A (en) System and method for pushing data relevant to working standard
CN110196833B (en) Application searching method, device, terminal and storage medium
CN111240558A (en) Information searching method, device, terminal and storage medium
CN110287304B (en) Question and answer information processing method and device and computer equipment
CN113486283B (en) Page merging method, device, server, medium and product
CN115292462A (en) Character generation method and device, mobile terminal, readable storage medium and chip
CN114816389A (en) Management system building method, device, equipment and medium based on meta-model
CN114047855A (en) Form editing method and device and terminal equipment
CN112235120A (en) Group combination method and electronic equipment
JP6934351B2 (en) AI service usage support system

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
GR01 Patent grant
GR01 Patent grant