CN106933848B - Information sending method and device - Google Patents
Information sending method and device Download PDFInfo
- Publication number
- CN106933848B CN106933848B CN201511020894.1A CN201511020894A CN106933848B CN 106933848 B CN106933848 B CN 106933848B CN 201511020894 A CN201511020894 A CN 201511020894A CN 106933848 B CN106933848 B CN 106933848B
- Authority
- CN
- China
- Prior art keywords
- information
- keyword
- standard information
- standard
- keywords
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses an information sending method, which comprises the following steps: receiving ith question information sent by a terminal; determining standard information and recommendation information corresponding to the ith question information from a first database, wherein the recommendation information is other standard information capable of recommending service for the ith question information; and sending the standard information and the recommendation information to the terminal. The embodiment of the invention also discloses an information sending device.
Description
Technical Field
The present invention relates to recommendation system technologies, and in particular, to an information sending method and apparatus.
Background
With the continuous development of the internet and the increasing prevalence of electronic commerce, users need to browse mass data at each large website every day. The customer service platforms of the operators provide response systems for users, and answer various service queries and problems related to operation processes proposed by the users.
The existing answering system mainly comprises: recommending services or commodities for the inquiry of the user according to the manual customer service familiar with the services; inquiring and matching services or commodities containing the same vocabulary according to a keyword matching technology input by a user; and classifying the users, and recommending the services or commodities to the users according to the hot words purchased or inquired by the users of the same type.
However, although the manual customer service can accurately answer the questions of the user and give the user corresponding recommendation options, the operation cost is too high, the keyword matching technology and the hot word recommendation technology cannot accurately find the services in which the user is interested, only a rough answer set can be returned, and the user experience is reduced.
Disclosure of Invention
In order to solve the above technical problems, embodiments of the present invention are expected to provide an information sending method and apparatus, which can improve user experience while reducing cost.
The technical scheme of the invention is realized as follows:
in a first aspect, an information sending method is provided, where the method includes:
receiving ith question information sent by a terminal, wherein i is a positive integer;
determining standard information and recommendation information corresponding to the ith question information from a first database, wherein the recommendation information is other standard information capable of recommending service for the ith question information;
and sending the standard information and the recommendation information to the terminal.
Optionally, the determining, from the first database, the target information and the recommendation information corresponding to the ith question information includes:
acquiring first keywords of the first i pieces of question information;
when the first keyword is a keyword of the first database, determining standard information corresponding to the first keyword in the first database;
searching a plurality of standard information related to the first keyword in the first database according to the first keyword;
determining output priorities of the plurality of standard information;
determining n standard information with the highest output priority in the plurality of standard information, wherein n is a positive integer;
and taking the n standard information with the highest output priority as the recommendation information.
Optionally, after the sending of the recommendation information to the terminal, the method further includes:
receiving the (i + 1) th question information sent by the terminal;
and updating the first database according to the (i + 1) th question information.
Optionally, the updating the first database according to the (i + 1) th question information further includes:
acquiring a second keyword of the (i + 1) th question information;
when the second keyword comprises a keyword of the second database and the i +1 th question information does not comprise an indication of receiving a user to check the n pieces of recommended information, reducing the weight of the standard information and the n pieces of recommended information in the first database;
when the second keyword comprises a keyword of the second database and the i +1 th question information comprises an indication of receiving a user to check first recommendation information in the n recommendation information, improving the weight of the first recommendation information;
when the second keyword does not include the keyword of the second database and the i +1 th question information includes an indication for receiving a user to check first recommendation information in the n recommendation information, improving the weight of the standard information and the first recommendation information;
when the second keyword does not include the keyword of the second database and the i +1 th question information does not include an indication for receiving a user to check the first recommendation information in the n recommendation information, increasing the weight of the standard information;
and when the second keyword is the same as the first keyword, reducing the weight of the standard information and the recommendation information.
Optionally, the increasing the weight of the first recommendation information includes:
judging whether a path from the second keyword to the standard information exists or not;
if the path from the second keyword to the standard information exists, deleting the path from the second keyword to the standard information, and improving the weight of the first recommendation information;
and if the path from the second keyword to the standard information does not exist, adding the second keyword into the upper keywords corresponding to the standard information, and improving the weight of the first recommendation information.
Optionally, after the increasing the weight of the standard information, the method further includes:
and adding the second keyword to the upper keywords of the keywords corresponding to the standard information.
Optionally, when the second keyword is the same as the first keyword, the reducing the weight of the standard information and the recommendation information includes:
when both the standard information and the recommendation information cannot answer the question information, reducing the weight of the standard information and the recommendation information;
when the standard information and the recommendation information are not enough to meet the query of the user, different keywords in the first keywords and the second keywords are determined; and in the first database, the different keywords are used as lower keywords of the common keywords in the keywords corresponding to the standard questions and the keywords corresponding to the recommendation information.
Optionally, the first database further includes weights of each standard information, and the searching, according to the first keyword, a plurality of standard information associated with the first keyword in the first database includes:
determining at least one matching path corresponding to the first keyword in the first database;
according to the matching path, determining first standard information corresponding to the matching path and keywords of the first standard information;
determining at least one query path corresponding to a keyword of the first standard information in a first database;
the query process is circulated until the keyword can not determine the query path position any more;
taking the standard information corresponding to the determined query path as a plurality of standard information associated with the first keyword;
the determining the output priority of the plurality of standard information includes:
acquiring the number of the keywords of each query path;
acquiring the circulating times of each query path;
determining a first sequence number of the standard information corresponding to each query path according to the number of the keywords of each query path and the circulating times of each query path;
acquiring the weight of the standard information corresponding to each query path;
determining a second sequence number of the standard information corresponding to each query path according to the weight of the standard information corresponding to each query path;
and determining the output priority of the standard information corresponding to each query path according to the first sequence number and the second sequence number of the standard information corresponding to each query path.
Optionally, the first database further includes a correspondence between a keyword of the hotspot event and the service feature; after determining the second sequence number of the standard information corresponding to each query path according to the weight of the standard information corresponding to each query path, the method further includes:
when a first hot event occurs, acquiring a third keyword of the first hot event;
determining the service characteristics corresponding to the third key words in the first database; the traffic characteristic is a percentage increase in traffic usage;
acquiring a user service and the transaction amount of the user service;
determining the expected usage amount of the user service according to the user service and the corresponding service characteristics;
determining standard information which is closest to the expected usage amount of the user service in the first database according to the expected usage amount of the user service;
determining a third sequence number of the closest standard information according to the difference between the expected usage amount of the user service and the handling amount of the corresponding service;
determining the average sequence number of the standard problems with the first sequence number, the second sequence number and the third sequence number according to the third sequence number of the closest standard information and the first sequence number and the second sequence number of the standard information corresponding to each query path;
determining the output priority of the standard information with the first sequence number, the second sequence number and the third sequence number according to the average sequence number;
the standard information having the first sequence number and the second sequence number is taken as the standard information having the lowest output priority.
Optionally, the method further includes:
acquiring each hot event which occurs in history;
extracting keywords of each hotspot event;
acquiring service conditions of each service when hot events with the same keywords occur;
generating service characteristics of the hot events with the same keywords according to the service use conditions of the services;
and storing the corresponding relation between the keywords of each hotspot event and the service characteristics.
In a second aspect, an information transmitting apparatus is provided, the apparatus including:
the terminal comprises a receiving unit, a sending unit and a receiving unit, wherein the receiving unit is used for receiving ith question information sent by the terminal, and i is a positive integer;
the determining unit is used for determining standard information and recommendation information corresponding to the ith question information from a first database, wherein the recommendation information is other standard information capable of recommending service for the ith question information;
and the sending unit is used for sending the standard information and the recommendation information to the terminal.
Optionally, the determining unit is specifically configured to:
the acquiring subunit is used for acquiring first keywords of the first i pieces of question information;
a determining subunit, configured to determine, in the first database, standard information corresponding to the first keyword when the first keyword is a keyword of the first database;
the searching subunit is used for searching a plurality of standard information related to the first keyword in the first database according to the first keyword;
the determining subunit is configured to determine output priorities of the plurality of standard information; determining n standard information with the highest output priority in the plurality of standard information, wherein n is a positive integer; and taking the n standard information with the highest output priority as the recommendation information.
Optionally, the receiving unit is further configured to receive the (i + 1) th question information sent by the terminal;
the device further comprises:
and the updating unit is used for updating the first database according to the (i + 1) th question information.
Optionally, the first database further includes weights of each standard information, and the updating unit is specifically configured to:
acquiring a second keyword of the (i + 1) th question information;
when the second keyword comprises a keyword of the second database and the i +1 th question information does not comprise an indication of receiving a user to check the n pieces of recommended information, reducing the weight of the standard information and the n pieces of recommended information in the first database;
when the second keyword comprises a keyword of the second database and the i +1 th question information comprises an indication of receiving a user to check first recommendation information in the n recommendation information, improving the weight of the first recommendation information;
when the second keyword does not include the keyword of the second database and the i +1 th question information includes an indication for receiving a user to check first recommendation information in the n recommendation information, improving the weight of the standard information and the first recommendation information;
when the second keyword does not include the keyword of the second database and the i +1 th question information does not include an indication for receiving a user to check the first recommendation information in the n recommendation information, increasing the weight of the standard information;
and when the second keyword is the same as the first keyword, reducing the weight of the standard information and the recommendation information.
Optionally, the updating unit is further configured to:
judging whether a path from the second keyword to the standard information exists or not;
if the path from the second keyword to the standard information exists, deleting the path from the second keyword to the standard information, and improving the weight of the first recommendation information;
and if the path from the second keyword to the standard information does not exist, adding the second keyword into the upper keywords corresponding to the standard information, and improving the weight of the first recommendation information.
Optionally, the apparatus further comprises:
and the processing unit is used for adding the second keyword to the upper keywords of the keywords corresponding to the standard information.
Optionally, the updating unit is further configured to:
when both the standard information and the recommendation information cannot answer the question information, reducing the weight of the standard information and the recommendation information;
when the standard information and the recommendation information are not enough to meet the query of the user, different keywords in the first keywords and the second keywords are determined; and in the first database, the different keywords are used as lower keywords of the common keywords in the keywords corresponding to the standard questions and the keywords corresponding to the recommendation information.
Optionally, the first database further includes weights of each standard information, and the search subunit is specifically configured to:
determining at least one matching path corresponding to the first keyword in the first database;
according to the matching path, determining first standard information corresponding to the matching path and keywords of the first standard information;
determining at least one query path corresponding to a keyword of the first standard information in a first database;
the query process is circulated until the keyword can not determine the query path position any more;
taking the standard information corresponding to the determined query path as a plurality of standard information associated with the first keyword;
the determining subunit is specifically configured to:
acquiring the number of the keywords of each query path;
acquiring the circulating times of each query path;
determining a first sequence number of the standard information corresponding to each query path according to the number of the keywords of each query path and the circulating times of each query path;
acquiring the weight of the standard information corresponding to each query path;
determining a second sequence number of the standard information corresponding to each query path according to the weight of the standard information corresponding to each query path;
and determining the output priority of the standard information corresponding to each query path according to the first sequence number and the second sequence number of the standard information corresponding to each query path.
Optionally, the first database further includes a correspondence between a keyword of the hotspot event and the service feature; the device further comprises:
the acquiring unit is used for acquiring a third keyword of a first hot event when the first hot event occurs; acquiring a user service and the transaction amount of the user service;
the determining unit is further configured to determine, in the first database, a service feature corresponding to the third keyword; the traffic characteristic is a percentage increase in traffic usage; determining the expected usage amount of the user service according to the user service and the corresponding service characteristics; determining standard information which is closest to the expected usage amount of the user service in the first database according to the expected usage amount of the user service; determining a third sequence number of the closest standard information according to the difference between the expected usage amount of the user service and the handling amount of the corresponding service; determining the average sequence number of the standard problems with the first sequence number, the second sequence number and the third sequence number according to the third sequence number of the closest standard information and the first sequence number and the second sequence number of the standard information corresponding to each query path; determining the output priority of the standard information with the first sequence number, the second sequence number and the third sequence number according to the average sequence number; the standard information having the first sequence number and the second sequence number is taken as the standard information having the lowest output priority.
Optionally, the obtaining unit is further configured to obtain each hotspot event that occurs historically; acquiring keywords of each hotspot event; acquiring service conditions of each service when hot events with the same keywords occur;
the device further comprises:
a generating unit, configured to generate service features of the hot events with the same keyword according to the service usage conditions;
and the storage unit is used for storing the corresponding relation between the keywords of each hotspot event and the service characteristics. The embodiment of the invention provides an information sending method and device, which comprises the steps of firstly receiving ith question information sent by a terminal; determining standard information and recommendation information corresponding to the ith question information from a first database according to the ith question information, wherein the recommendation information is other standard information capable of recommending service for the ith question information; and then, transmitting the standard information and the recommendation information to the terminal. Therefore, the user questions (question information) sent by the terminal can not only give out standard information, but also give out recommendation information, and therefore, even if the standard information is not the correct answer corresponding to the user questions, the recommendation information can also be the correct answer, the satisfaction degree of the user is increased, the user experience is improved, meanwhile, the recommendation information and the standard information are both automatically replied information, manual operation is avoided, and therefore labor cost is saved.
Drawings
Fig. 1 is a flowchart of an information sending method according to an embodiment of the present invention;
fig. 2 is a flowchart of another information sending method according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an information sending apparatus according to an embodiment of the present invention;
fig. 4 is a schematic diagram of another information sending apparatus according to an embodiment of the present invention;
fig. 5 is a schematic diagram of another information sending apparatus according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Example one
The embodiment of the invention provides an information sending method, which is applied to an information sending device, wherein the information sending device can be a server. As shown in fig. 1, the method includes:
and step 101, receiving the ith question information sent by the terminal.
Here, i is a positive integer, and the quiz information is a sentence that the user uses to consult with the business or goods, for example, "what is my credit balance? "; the question sentence may also be a negative emotional sentence, e.g., "bad thoroughly", "don't go at all", etc.
And 102, determining standard information and recommendation information corresponding to the ith question information from a first database according to the ith question information.
Here, the recommendation information is other standard information capable of recommending a service for the ith question information; the first database stores standard information, keywords, and paths corresponding thereto.
Specifically, first keywords of the first i pieces of question information are obtained; when the first keyword is a keyword of a first database, determining standard information corresponding to the first keyword in the first database; searching a plurality of standard information related to the first keyword in a first database according to the first keyword; determining output priorities of a plurality of standard information; determining n standard information with highest output priority in the plurality of standard information, wherein n is a positive integer; and taking the n standard information with the highest output priority as the recommendation information. Here, the first database includes not only keywords but also semantic relationships between the keywords. For example, the keyword "package" has many sub-services, such as "flying package", "travel package", "self-service package", and "internet package". Then, in the knowledge base, the following four service keywords and the keyword "package" are the relationship between the lower semantic level and the upper semantic level, and the upper and lower semantic level relationship can be represented by dividing the triple "upper word" - "into" - "lower word". That is to say, "package" is the upper keyword, "flying to enjoy package", "business travel package", "self-selection package" and "internet package" are the lower keywords of "package". Therefore, all keywords have such semantic relationships between top and bottom.
It should be noted that since each province has many services, if service recommendation is performed on users only according to keyword matching inquired by the users, redundant recommendation is easily caused. For example, if the keyword queried by the user is "how to handle a business trip package", only according to the way of matching the keyword, the corresponding standard information is: "4G package introduction", "cancel 4G package", "4G business travel package introduction", "open 4G business travel package", and the like. If the keyword matching is performed through the triples in the first database, the standard information with a far service logic relationship, such as "introduction of 4G package" and "cancellation of 4G package" will be filtered, and only the standard information with a close service logic relationship, such as "introduction of 4G travel package" and "opening of 4G travel package", will be left.
Further, the first database further includes a weight of each standard information, and the searching, according to the first keyword, a plurality of standard information associated with the first keyword in the first database includes: determining at least one matching path corresponding to the first keyword in the first database; according to the matching path, determining first standard information corresponding to the matching path and keywords of the first standard information; determining at least one query path corresponding to a keyword of the first standard information in a first database; the query process is circulated until the keyword can not determine the query path position any more; and taking the standard information corresponding to the determined query path as a plurality of standard information relevant to the first keyword. Here, finding each finding path related to the first keyword may include: matching paths according to the labeling information in the first database, and then inquiring each matching path as follows: continuously searching a first search path of the triple taking the matching path as a third element, and then searching the first search path of the triple taking the first search path as the third search path, and exhausting the process until no triple can be inquired, recording all paths in the search process, and further recording the number of the triples contained in each path and the number of the keywords corresponding to each search path; the number of triples is the number of cycles of each query path.
Further, the determining the output priority of the plurality of standard information includes: acquiring the number of the keywords of each query path; acquiring the circulating times of each query path; determining a first sequence number of the standard information corresponding to each query path according to the number of the keywords of each query path and the circulating times of each query path; acquiring the weight of the standard information corresponding to each query path; determining a second sequence number of the standard information corresponding to each query path according to the weight of the standard information corresponding to each query path; and determining the output priority of the standard information corresponding to each query path according to the first sequence number and the second sequence number of the standard information corresponding to each query path. Here, the number of times of query path circulation refers to the number of times of circulation when starting from the query path, performing circulation query once and until the query path cannot be queried any more; the more the number of the keywords is, the smaller the first sequence number of the standard information is, the more the cycle times of the query path is, and otherwise, the larger the first sequence number of the standard information is; the standard information with larger weight value has smaller second sequence number.
The first database also comprises a corresponding relation between the keywords of the hotspot event and the service characteristics; after determining the second sequence number of the standard information corresponding to each query path according to the weight of the standard information corresponding to each query path, the method further includes: when the first hot event occurs, acquiring a third keyword of the first hot event; determining the service characteristics corresponding to the third key words in the first database; the traffic characteristic is a percentage increase in traffic usage; acquiring a user service and the transaction amount of the user service; determining the expected usage amount of the user service according to the user service and the corresponding service characteristics; determining standard information which is closest to the expected usage amount of the user service in the first database according to the expected usage amount of the user service; determining a third sequence number of the closest standard information according to the difference between the expected usage amount of the user service and the handling amount of the corresponding service; determining the average sequence number of the standard problems with the first sequence number, the second sequence number and the third sequence number according to the third sequence number of the closest standard information and the first sequence number and the second sequence number of the standard information corresponding to each query path; determining the output priority of the standard information with the first sequence number, the second sequence number and the third sequence number according to the average sequence number; the standard information having the first sequence number and the second sequence number is taken as the standard information having the lowest output priority.
And 103, sending the standard information and the recommendation information to the terminal.
After step 103, the method further comprises: receiving the (i + 1) th question information sent by the terminal; and updating the first database according to the (i + 1) th question information.
Further, the first database further includes weights of each standard information, and the updating the first database according to the (i + 1) th question information specifically includes: acquiring a second keyword of the (i + 1) th question information; when the second keyword comprises a keyword of a second database and the i +1 th question information does not comprise an indication for receiving the user to check the n pieces of recommended information, reducing the weight of the standard information and the n pieces of recommended information in the first database; when the second keyword comprises a keyword of a second database and the (i + 1) th question information comprises an instruction for receiving a user to check first recommendation information in the n recommendation information, improving the weight of the first recommendation information; when the second keyword does not comprise the keyword of the second database and the i +1 th question information comprises an indication for receiving a user to check the first recommendation information in the n recommendation information, improving the weight of the standard information and the first recommendation information; when the second keyword does not comprise the keyword of the second database and the i +1 th question information does not comprise an indication for receiving a user to check the first recommendation information in the n recommendation information, the weight of the standard information is increased; and when the second keyword is the same as the first keyword, reducing the weight of the standard information and the recommendation information.
Further, the increasing the weight of the first recommendation information includes: judging whether a path from the second keyword to the standard information exists or not; if the path from the second keyword to the standard information exists, deleting the path from the second keyword to the standard information, and improving the weight of the first recommendation information; and if the path from the second keyword to the standard information does not exist, adding the second keyword into the keyword corresponding to the standard information, and improving the weight of the first recommendation information.
Further, after the increasing the weight of the standard information, the method further includes: and adding the second keyword to the upper keywords of the keywords corresponding to the standard information.
Further, the reducing the weight of the standard information and the recommendation information when the first keyword is the same as the second keyword includes: when both the standard information and the recommendation information cannot answer the question information, reducing the weight of the standard information and the recommendation information; when the standard information and the recommendation information are not enough to meet the query of the user, different keywords in the first keywords and the second keywords are determined; and in the first database, the different keywords are used as lower keywords of the common keywords in the keywords corresponding to the standard questions and the keywords corresponding to the recommendation information. Here, the i +1 th question information input by the user is analyzed, and whether the standard information and the recommendation information answer the question of the question information can be determined from the analysis result; or whether the question is partially answered with questioning information.
Further, the method further comprises: acquiring each hot event which occurs in history; acquiring keywords of each hotspot event; acquiring service conditions of each service when hot events with the same keywords occur; generating service characteristics of the hot events with the same keywords according to the service use conditions of the services; and storing the corresponding relation between the keywords of each hotspot event and the service characteristics.
Therefore, the user questions (question information) sent by the terminal can not only give out standard information, but also give out recommendation information, and therefore, even if the standard information is not the correct answer corresponding to the user questions, the recommendation information can also be the correct answer, the satisfaction degree of the user is increased, the user experience is improved, meanwhile, the recommendation information and the standard information are both automatically replied information, manual operation is avoided, and therefore labor cost is saved.
Example two
An embodiment of the present invention provides an information sending method, which is applied to a network automatic reply system, where the system includes a terminal and a server for communication, as shown in fig. 2, a station of the embodiment introduces at a server side, and the method includes:
Here, i is a positive integer.
For example, the questioning information is "please tell me, how much my data traffic remains? "the keywords obtained by the server are" data traffic "," remaining ", and" how much "; the questioning information may also be "completely useless", and the first keyword acquired by the server is "useless".
Step 203, when the first keyword of the ith question information is the keyword of the first database, acquiring the keywords of the first i-1 question information.
In particular, the knowledge base may comprise at least two databases, a first database storing keywords, standard information and path relations thereof, and a second database storing keywords of negative emotions, such as "wrong", "not used at all". It should be noted that when the first keyword does not belong to the first database or the second database, the first keyword is equivalent to being absent.
And step 204, determining standard information corresponding to the ith question information from the knowledge base according to the keywords of the first i question information.
And step 205, determining recommendation information corresponding to the ith piece of tweet information from a knowledge base according to the keywords of the previous i pieces of question information.
Specifically, a plurality of path relationships corresponding to the keywords of the previous i pieces of question information are obtained from the first database, and taking one of the path relationships as an example, in the path relationship, all the keywords associated with the path relationship, the number of triples of the path relationship are determined, specifically, the following relationship query is performed on each path relationship: continuously searching a first path relation of the triple with the path relation as a third element, searching a first path relation of a next triple with the first path relation as the third path relation, exhausting the process until no triple can be inquired, recording all paths in the searching process, recording the number of the triples contained in each path, correspondingly determining the path relations corresponding to the path relations, sequencing the paths with more keywords and more triples to obtain a first sequence, and combining the corresponding standard information in each path relation in the first sequence into a standard information set; sorting the standard information according to the existing weights of the standard information to obtain a second sequence; determining all recommendable services and actual increase proportions according to the increase proportion of services deduced from a preset hot spot event and the services handled by a user corresponding to a terminal, generating a standard information set corresponding to the recommendable services, and obtaining a third sequence by sequencing according to the difference value between the increase proportions and the actual increase proportions in each standard information from large to small; and averaging the serial numbers of the standard information in the first sequence, the second sequence and the third sequence, sorting the standard information according to the average value, and sending the first five pieces of standard information to the terminal as recommendation information.
Here, the above query process is equivalent to searching for the upper path of the path relationship until the uppermost path relationship is found. For example, the upper path layer of the "4G flyout service" is the "4G service" and the "flyout service", the upper path layer of the "flyout service" is the "dynamic zone campus traffic service", and the upper path layer of the "dynamic zone campus traffic" is the "dynamic zone service". The hierarchy of the upper path of the "4G flyoung service" is 4 layers, that is, the number of triples is 4.
And step 206, sending the standard information and the recommendation information corresponding to the ith question information to the terminal.
Here, the standard information and the recommendation information may be transmitted in the form of audio or may be transmitted in the form of text such as a short message. The standard information and the recommendation information of the embodiment are sent to the terminal in a short message mode.
And step 207, receiving the (i + 1) th question information sent by the terminal.
And step 208, extracting keywords from the (i + 1) th questioning information.
And 209, when the keywords of the (i + 1) th questioning information are the keywords of the first database and the user clicks the recommendation information is not received, reducing the weight of the (i) th standard information and the recommendation information. And ending the process.
Here, the non-reception of the user click recommendation information may be three cases, that is, an operation of not receiving the user click recommendation information within a predetermined time, receiving the (i + 2) th question information sent by the terminal, or stopping communication between the terminal and the server.
Step 210, when the (i + 1) th question information keyword is a keyword of the first database and an operation of clicking recommendation information by a user is received, judging whether a path relation between the ith question information keyword and standard information exists. If yes, go to step 210; if not, go to step 211.
And step 211, deleting the path relation between the keywords of the ith question information and the standard information, and increasing the weight of the recommendation information of the ith question information. And ending the process.
And step 212, increasing the weight of the recommendation information of the ith question information.
And step 213, adding the keywords of the ith question information into the upper keywords corresponding to the standard information, and ending the process.
And step 214, when the i +1 th question information keyword is not the keyword of the first database or the second database and the operation of clicking the recommendation information by the user is received, increasing the weight of the recommendation information and the standard information of the i th question information and ending the process.
Specifically, the adding of the upper keywords of the keyword of the ith question information includes: and acquiring keywords corresponding to the standard information of the ith question information, deleting the keywords which are not stored in the second database in the standard keywords, and supplementing the keywords of the ith question information into the upper keywords of the keywords.
Here, the keyword is a stem content in the standard information, for example: the standard information is "query voice tariff" and the keywords are "query", "voice" and "tariff", respectively. Since most of the data stored in the second database are spoken keywords, that is, keywords with a relatively high frequency of use by the user, and the standard keywords are not frequently used, for example, the spoken keywords corresponding to the standard keywords "tariff" are "telephone charges". There are few "charges" for people, and most people use "charges". Therefore, the standard keywords which are not used at ordinary times are deleted, and the space memory of the second database is saved.
It should be noted that the keywords in this embodiment are related in upper and lower positions.
EXAMPLE III
An embodiment of the present invention provides an information sending apparatus 30, as shown in fig. 3, where the apparatus 30 includes:
a receiving unit 301, configured to receive the ith question information sent by the terminal, where i is a positive integer.
A determining unit 302, configured to determine, from a first database, standard information and recommendation information corresponding to the ith question information, where the recommendation information is other standard information capable of recommending a service for the ith question information.
A sending unit 303, configured to send the standard information and the recommendation information to the terminal.
Therefore, the user questions (question information) sent by the terminal can not only give out standard information, but also give out recommendation information, and therefore, even if the standard information is not the correct answer corresponding to the user questions, the recommendation information can also be the correct answer, the satisfaction degree of the user is increased, the user experience is improved, meanwhile, the recommendation information and the standard information are both automatically replied information, manual operation is avoided, and therefore labor cost is saved.
Further, as shown in fig. 4, the determining unit 302 is specifically configured to:
an acquiring subunit 3021, configured to acquire first keywords of the first i pieces of question information;
a determining subunit 3022, configured to determine, in the first database, standard information corresponding to the first keyword;
a search subunit 3023, configured to search the first database for a plurality of standard information associated with the first keyword according to the first keyword;
the determining subunit 3022 is configured to determine output priorities of the plurality of standard information; determining n standard information with the highest output priority in the plurality of standard information, wherein n is a positive integer; and taking the n standard information with the highest output priority as the recommendation information.
Further, the receiving unit 301 is further configured to receive the (i + 1) th question information sent by the terminal;
as shown in fig. 5, the apparatus 30 further includes:
an updating unit 304, configured to update the first database according to the (i + 1) th question information.
Further, the first database further includes a weight of each standard information, and the updating unit 304 is specifically configured to:
acquiring a second keyword of the (i + 1) th question information;
when the second keyword comprises a keyword of the second database and the i +1 th question information does not comprise an indication of receiving a user to check the n pieces of recommended information, reducing the weight of the standard information and the n pieces of recommended information in the first database;
when the second keyword comprises a keyword of the second database and the i +1 th question information comprises an indication of receiving a user to check first recommendation information in the n recommendation information, improving the weight of the first recommendation information;
when the second keyword does not include the keyword of the second database and the i +1 th question information includes an indication for receiving a user to check first recommendation information in the n recommendation information, improving the weight of the standard information and the first recommendation information;
when the second keyword does not include the keyword of the second database and the i +1 th question information does not include an indication for receiving a user to check the first recommendation information in the n recommendation information, increasing the weight of the standard information;
and when the second keyword is the same as the first keyword, reducing the weight of the standard information and the recommendation information.
Further, the updating unit 304 is further configured to:
judging whether a path from the second keyword to the standard information exists or not;
if the path from the second keyword to the standard information exists, deleting the path from the second keyword to the standard information, and improving the weight of the first recommendation information;
and if the path from the second keyword to the standard information does not exist, adding the second keyword into the keyword corresponding to the standard information, and improving the weight of the first recommendation information.
Further, as shown in fig. 5, the apparatus 30 further includes:
the processing unit 305 is configured to add the second keyword to an upper keyword of the keyword corresponding to the standard information.
Further, the updating unit 304 is further configured to:
when both the standard information and the recommendation information cannot answer the question information, reducing the weight of the standard information and the recommendation information;
when the standard information and the recommendation information are not enough to meet the query of the user, different keywords in the first keywords and the second keywords are determined; and in the first database, the different keywords are separated from the keywords corresponding to the standard questions and the keywords corresponding to the recommendation information.
Further, the first database further includes a weight of each standard information, and the search subunit 3023 is specifically configured to:
determining at least one matching path corresponding to the first keyword in the first database;
according to the matching path, determining first standard information corresponding to the matching path and keywords of the first standard information;
determining at least one query path corresponding to a keyword of the first standard information in a first database;
the query process is circulated until the keyword can not determine the query path position any more;
taking the standard information corresponding to the determined query path as a plurality of standard information associated with the first keyword;
the determining subunit 3022 is specifically configured to:
acquiring the number of the keywords of each query path;
acquiring the circulating times of each query path;
determining a first sequence number of the standard information corresponding to each query path according to the number of the keywords of each query path and the circulating times of each query path;
acquiring the weight of the standard information corresponding to each query path;
determining a second sequence number of the standard information corresponding to each query path according to the weight of the standard information corresponding to each query path;
and determining the output priority of the standard information corresponding to each query path according to the first sequence number and the second sequence number of the standard information corresponding to each query path.
Further, the first database further comprises a corresponding relation between the keywords of the hotspot event and the service features; as shown in fig. 5, the apparatus 30 further includes:
an obtaining unit 306, configured to obtain a third keyword of a first hotspot event when the first hotspot event occurs; acquiring a service of a user;
the determining unit 302 is further configured to determine, in the first database, a service feature corresponding to the third keyword; the traffic characteristic is a percentage increase in traffic usage; determining the expected usage amount of the user service according to the user service and the corresponding service characteristics; determining standard information which is closest to the expected usage amount of the user service in the first database according to the expected usage amount of the user service; determining a third sequence number of the closest standard information according to the difference between the expected usage amount of the user service and the handling amount of the corresponding service; determining the average sequence number of the standard problems with the first sequence number, the second sequence number and the third sequence number according to the third sequence number of the closest standard information and the first sequence number and the second sequence number of the standard information corresponding to each query path; determining the output priority of the standard information with the first sequence number, the second sequence number and the third sequence number according to the average sequence number; the standard information having the first sequence number and the second sequence number is taken as the standard information having the lowest output priority.
Further, the obtaining unit 306 is further configured to obtain each hot event that occurs historically; acquiring keywords of each hotspot event; acquiring service conditions of each service when hot events with the same keywords occur; as shown in fig. 5, the apparatus 30 further includes:
a generating unit 307, configured to generate service features of the hot events with the same keyword according to the service usage conditions;
the storage unit 308 is configured to store a corresponding relationship between the keywords and the service features of each hotspot event.
In practical applications, the receiving Unit 301, the determining Unit 302, the sending Unit 303, the updating Unit 304, the Processing Unit 305, the obtaining Unit 306, the generating Unit 307, and the storing Unit 308 may be implemented by a Central Processing Unit (CPU), a Microprocessor (MPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), or the like in the information sending apparatus 30.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (21)
1. An information sending method, characterized in that the method comprises:
receiving ith question information sent by a terminal, wherein i is a positive integer;
determining standard information and recommendation information corresponding to the ith question information from a first database, wherein the recommendation information is other standard information capable of recommending service for the ith question information;
sending the standard information and the recommendation information to the terminal;
wherein, the determining the standard information corresponding to the ith question information from the first database includes: acquiring first keywords of the first i pieces of question information; when the first keyword is a keyword of the first database, determining standard information corresponding to the first keyword in the first database.
2. The method according to claim 1, wherein the determining recommendation information corresponding to the ith question information from the first database comprises:
searching a plurality of standard information related to the first keyword in the first database according to the first keyword;
determining output priorities of the plurality of standard information;
determining n standard information with the highest output priority in the plurality of standard information, wherein n is a positive integer;
and taking the n standard information with the highest output priority as the recommendation information.
3. The method of claim 1, wherein after the sending the recommendation information to the terminal, the method further comprises:
receiving the (i + 1) th question information sent by the terminal;
and updating the first database according to the (i + 1) th question information.
4. The method according to claim 3, wherein the first database further includes a weight of each standard information, and the updating the first database according to the i +1 th question information includes:
acquiring a second keyword of the (i + 1) th question information;
when the second keyword comprises a keyword of a second database and the i +1 th question information does not comprise an indication for receiving a user to check the n pieces of recommended information, reducing the weight of the standard information and the n pieces of recommended information in the first database;
when the second keyword comprises a keyword of the second database and the i +1 th question information comprises an indication of receiving a user to check first recommendation information in the n recommendation information, improving the weight of the first recommendation information;
when the second keyword does not include the keyword of the second database and the i +1 th question information includes an indication for receiving a user to check first recommendation information in the n recommendation information, improving the weight of the standard information and the first recommendation information;
when the second keyword does not comprise a keyword of the second database and the i +1 th question information does not comprise an indication for receiving a user to select to view the first recommended information in the n pieces of recommended information, the weight of the standard information is increased;
and when the second keyword is the same as the first keyword, reducing the weight of the standard information and the recommendation information.
5. The method of claim 4, wherein the increasing the weight of the first recommendation information comprises:
judging whether a path from the second keyword to the standard information exists or not;
if the path from the second keyword to the standard information exists, deleting the path from the second keyword to the standard information, and improving the weight of the first recommendation information;
and if the path from the second keyword to the standard information does not exist, adding the second keyword into the upper keywords corresponding to the standard information, and improving the weight of the first recommendation information.
6. The method of claim 4, wherein after the increasing the weight of the standard information, the method further comprises:
and adding the second keyword to the upper keywords of the keywords corresponding to the standard information.
7. The method of claim 4, wherein the reducing the weight of the standard information and the recommendation information when the second keyword is the same as the first keyword comprises:
when both the standard information and the recommendation information cannot answer the question information, reducing the weight of the standard information and the recommendation information;
when the standard information and the recommendation information are not enough to meet the query of the user, different keywords in the first keywords and the second keywords are determined; and in the first database, the different keywords are used as lower keywords of the common keywords in the keywords corresponding to the standard questions and the keywords corresponding to the recommendation information.
8. The method of claim 2, wherein the first database further includes a weight value of each standard information, and the searching the first database for the plurality of standard information associated with the first keyword according to the first keyword comprises:
determining at least one matching path corresponding to the first keyword in the first database;
according to the matching path, determining first standard information corresponding to the matching path and keywords of the first standard information;
determining at least one query path corresponding to a keyword of the first standard information in a first database;
the query process is circulated until the keyword can not determine the query path position any more;
taking the standard information corresponding to the determined query path as a plurality of standard information associated with the first keyword;
the determining the output priority of the plurality of standard information includes:
acquiring the number of the keywords of each query path;
acquiring the circulating times of each query path;
determining a first sequence number of the standard information corresponding to each query path according to the number of the keywords of each query path and the circulating times of each query path;
acquiring the weight of the standard information corresponding to each query path;
determining a second sequence number of the standard information corresponding to each query path according to the weight of the standard information corresponding to each query path;
and determining the output priority of the standard information corresponding to each query path according to the first sequence number and the second sequence number of the standard information corresponding to each query path.
9. The method of claim 8, wherein the first database further comprises a correspondence between keywords of the hotspot event and the business features; after determining the second sequence number of the standard information corresponding to each query path according to the weight of the standard information corresponding to each query path, the method further includes:
when a first hot event occurs, acquiring a third keyword of the first hot event;
determining the service characteristics corresponding to the third key words in the first database; the traffic characteristic is a percentage increase in traffic usage;
acquiring a user service and the transaction amount of the user service;
determining the expected usage amount of the user service according to the user service and the corresponding service characteristics;
determining standard information which is closest to the expected usage amount of the user service in the first database according to the expected usage amount of the user service;
determining a third sequence number of the closest standard information according to the difference between the expected usage amount of the user service and the handling amount of the corresponding service;
determining the average sequence number of the standard problems with the first sequence number, the second sequence number and the third sequence number according to the third sequence number of the closest standard information and the first sequence number and the second sequence number of the standard information corresponding to each query path;
determining the output priority of the standard information with the first sequence number, the second sequence number and the third sequence number according to the average sequence number;
the standard information having the first sequence number and the second sequence number is taken as the standard information having the lowest output priority.
10. The method of claim 9, further comprising:
acquiring each hot event which occurs in history;
extracting keywords of each hotspot event;
acquiring service conditions of each service when hot events with the same keywords occur;
generating service characteristics of the hot events with the same keywords according to the service use conditions of the services;
and storing the corresponding relation between the keywords of each hotspot event and the service characteristics.
11. An information transmission apparatus, characterized in that the apparatus comprises:
the terminal comprises a receiving unit, a sending unit and a receiving unit, wherein the receiving unit is used for receiving ith question information sent by the terminal, and i is a positive integer;
the determining unit is used for determining standard information and recommendation information corresponding to the ith question information from a first database, wherein the recommendation information is other standard information capable of recommending service for the ith question information;
a sending unit, configured to send the standard information and the recommendation information to the terminal;
wherein the determination unit includes: the acquiring subunit is used for acquiring first keywords of the first i pieces of question information; a determining subunit, configured to determine, in the first database, standard information corresponding to the first keyword when the first keyword is a keyword of the first database.
12. The apparatus of claim 11, wherein the determining unit further comprises:
the searching subunit is used for searching a plurality of standard information related to the first keyword in the first database according to the first keyword;
the determining subunit is configured to determine output priorities of the plurality of standard information; determining n standard information with the highest output priority in the plurality of standard information, wherein n is a positive integer; and taking the n standard information with the highest output priority as the recommendation information.
13. The apparatus according to claim 11, wherein the receiving unit is further configured to receive an i +1 th question message sent by the terminal;
the device further comprises:
and the updating unit is used for updating the first database according to the (i + 1) th question information.
14. The apparatus according to claim 13, wherein the first database further includes a weight of each standard information, and the updating unit is specifically configured to:
acquiring a second keyword of the (i + 1) th question information;
when the second keyword comprises a keyword of a second database and the i +1 th question information does not comprise an indication for receiving a user to check the n pieces of recommended information, reducing the weight of the standard information and the n pieces of recommended information in the first database;
when the second keyword comprises a keyword of the second database and the i +1 th question information comprises an indication of receiving a user to check first recommendation information in the n recommendation information, improving the weight of the first recommendation information;
when the second keyword does not include the keyword of the second database and the i +1 th question information includes an indication for receiving a user to check first recommendation information in the n recommendation information, improving the weight of the standard information and the first recommendation information;
when the second keyword does not comprise a keyword of the second database and the i +1 th question information does not comprise an indication for receiving a user to select to view the first recommended information in the n pieces of recommended information, the weight of the standard information is increased;
and when the second keyword is the same as the first keyword, reducing the weight of the standard information and the recommendation information.
15. The apparatus of claim 14, wherein the updating unit is further configured to:
judging whether a path from the second keyword to the standard information exists or not;
if the path from the second keyword to the standard information exists, deleting the path from the second keyword to the standard information, and improving the weight of the first recommendation information;
and if the path from the second keyword to the standard information does not exist, adding the second keyword into the upper keywords corresponding to the standard information, and improving the weight of the first recommendation information.
16. The apparatus of claim 14, further comprising:
and the processing unit is used for adding the second keyword to the upper keywords of the keywords corresponding to the standard information.
17. The apparatus of claim 14, wherein the updating unit is further configured to:
when both the standard information and the recommendation information cannot answer the question information, reducing the weight of the standard information and the recommendation information;
when the standard information and the recommendation information are not enough to meet the query of the user, different keywords in the first keywords and the second keywords are determined; and in the first database, the different keywords are used as lower keywords of the common keywords in the keywords corresponding to the standard questions and the keywords corresponding to the recommendation information.
18. The apparatus according to claim 12, wherein the first database further includes weights of each standard information, and the search subunit is specifically configured to:
determining at least one matching path corresponding to the first keyword in the first database;
according to the matching path, determining first standard information corresponding to the matching path and keywords of the first standard information;
determining at least one query path corresponding to a keyword of the first standard information in a first database;
the query process is circulated until the keyword can not determine the query path position any more;
taking the standard information corresponding to the determined query path as a plurality of standard information associated with the first keyword;
the determining subunit is specifically configured to:
acquiring the number of the keywords of each query path;
acquiring the circulating times of each query path;
determining a first sequence number of the standard information corresponding to each query path according to the number of the keywords of each query path and the circulating times of each query path;
acquiring the weight of the standard information corresponding to each query path;
determining a second sequence number of the standard information corresponding to each query path according to the weight of the standard information corresponding to each query path;
and determining the output priority of the standard information corresponding to each query path according to the first sequence number and the second sequence number of the standard information corresponding to each query path.
19. The apparatus of claim 18, wherein the first database further comprises a correspondence between keywords of a hotspot event and business features; the device further comprises:
the acquiring unit is used for acquiring a third keyword of a first hot event when the first hot event occurs; acquiring a user service and the transaction amount of the user service;
the determining unit is further configured to determine, in the first database, a service feature corresponding to the third keyword; the traffic characteristic is a percentage increase in traffic usage; determining the expected usage amount of the user service according to the user service and the corresponding service characteristics; determining standard information which is closest to the expected usage amount of the user service in the first database according to the expected usage amount of the user service; determining a third sequence number of the closest standard information according to the difference between the expected usage amount of the user service and the handling amount of the corresponding service; determining the average sequence number of the standard problems with the first sequence number, the second sequence number and the third sequence number according to the third sequence number of the closest standard information and the first sequence number and the second sequence number of the standard information corresponding to each query path; determining the output priority of the standard information with the first sequence number, the second sequence number and the third sequence number according to the average sequence number; the standard information having the first sequence number and the second sequence number is taken as the standard information having the lowest output priority.
20. The apparatus of claim 19,
the acquisition unit is further used for acquiring each hot event which occurs in history; acquiring keywords of each hotspot event; acquiring service conditions of each service when hot events with the same keywords occur;
the device further comprises:
a generating unit, configured to generate service features of the hot events with the same keyword according to the service usage conditions;
and the storage unit is used for storing the corresponding relation between the keywords of each hotspot event and the service characteristics.
21. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511020894.1A CN106933848B (en) | 2015-12-29 | 2015-12-29 | Information sending method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511020894.1A CN106933848B (en) | 2015-12-29 | 2015-12-29 | Information sending method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106933848A CN106933848A (en) | 2017-07-07 |
| CN106933848B true CN106933848B (en) | 2020-10-30 |
Family
ID=59442473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511020894.1A Active CN106933848B (en) | 2015-12-29 | 2015-12-29 | Information sending method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106933848B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287325A (en) * | 2019-06-28 | 2019-09-27 | 南方电网科学研究院有限责任公司 | Power grid customer service recommendation method and device based on intelligent voice analysis |
| WO2022229672A1 (en) * | 2021-04-27 | 2022-11-03 | Ip Ying Hoi Robert | Networked messaging systems and methods of allowing multiple companies operating on a value chain to serve a customer simultaneously |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101882291A (en) * | 2010-08-10 | 2010-11-10 | 万昌洵 | Problem-posing commodity information consultation method based on search engine technique |
| CN104239020A (en) * | 2013-06-21 | 2014-12-24 | Sap欧洲公司 | Decision-making standard driven recommendation |
| CN104699693A (en) * | 2013-12-05 | 2015-06-10 | 中国移动通信集团广东有限公司 | Information processing method and device thereof |
| CN105100165A (en) * | 2014-05-20 | 2015-11-25 | 深圳市腾讯计算机系统有限公司 | Network service recommendation method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4538756B2 (en) * | 2007-12-03 | 2010-09-08 | ソニー株式会社 | Information processing apparatus, information processing terminal, information processing method, and program |
| JP5637395B2 (en) * | 2011-05-24 | 2014-12-10 | 株式会社Ｊｖｃケンウッド | Information selection device, information selection method, terminal device, and computer program |
-
2015
- 2015-12-29 CN CN201511020894.1A patent/CN106933848B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101882291A (en) * | 2010-08-10 | 2010-11-10 | 万昌洵 | Problem-posing commodity information consultation method based on search engine technique |
| CN104239020A (en) * | 2013-06-21 | 2014-12-24 | Sap欧洲公司 | Decision-making standard driven recommendation |
| CN104699693A (en) * | 2013-12-05 | 2015-06-10 | 中国移动通信集团广东有限公司 | Information processing method and device thereof |
| CN105100165A (en) * | 2014-05-20 | 2015-11-25 | 深圳市腾讯计算机系统有限公司 | Network service recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106933848A (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9020138B1 (en) | Targeted issue routing | |
| CN106874492B (en) | Searching method and device | |
| US9247061B2 (en) | Answer based agent routing and display method | |
| US8935192B1 (en) | Social search engine | |
| US10885529B2 (en) | Automated upsells in customer conversations | |
| CN110909182B (en) | Multimedia resource searching method, device, computer equipment and storage medium | |
| CN110473040B (en) | Product recommendation method and device and electronic equipment | |
| US20140379745A1 (en) | Recommendation of search keywords based on indication of user intention | |
| US20110106895A1 (en) | Social search engine | |
| CN108335131B (en) | Method and device for estimating age bracket of user and electronic equipment | |
| CN108765051B (en) | Item recommendation method and device | |
| CN108932646B (en) | User tag verification method and device based on operator and electronic equipment | |
| EP3262589A1 (en) | Proactive knowledge offering system and method | |
| CN112966081A (en) | Method, device, equipment and storage medium for processing question and answer information | |
| CN105812473B (en) | Data processing method and device | |
| CN111756796B (en) | Method and device for pushing rights and interests resource information, storage medium and terminal | |
| KR20180017085A (en) | Location information providing method and device | |
| WO2019133759A1 (en) | Data processing method, apparatus, device and computer readable storage media | |
| CN106933848B (en) | Information sending method and device | |
| CN113806634B (en) | Service package recommending method, device and server | |
| CN111461827A (en) | Product evaluation information pushing method and device | |
| CN107465797B (en) | Incoming call information display method and device for terminal equipment | |
| CN106485520B (en) | Cross-channel communication control method and server | |
| CN113343095A (en) | Model training and information recommendation method and device | |
| CN106682030A (en) | Method and device for information processing |
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 |