CN106933848A - A kind of method for sending information and device - Google Patents

A kind of method for sending information and device Download PDF

Info

Publication number
CN106933848A
CN106933848A CN201511020894.1A CN201511020894A CN106933848A CN 106933848 A CN106933848 A CN 106933848A CN 201511020894 A CN201511020894 A CN 201511020894A CN 106933848 A CN106933848 A CN 106933848A
Authority
CN
China
Prior art keywords
keyword
information
standard information
database
standard
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.)
Granted
Application number
CN201511020894.1A
Other languages
Chinese (zh)
Other versions
CN106933848B (en
Inventor
范正洁
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.)
China Mobile Communications Group Co Ltd
Original Assignee
China Mobile Communications Group Co 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 China Mobile Communications Group Co Ltd filed Critical China Mobile Communications Group Co Ltd
Priority to CN201511020894.1A priority Critical patent/CN106933848B/en
Publication of CN106933848A publication Critical patent/CN106933848A/en
Application granted granted Critical
Publication of CN106933848B publication Critical patent/CN106933848B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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

Abstract

The embodiment of the invention discloses a kind of method for sending information, including：I-th question information that receiving terminal sends；The corresponding standard information of i-th question information and recommendation information are determined from the first database, the recommendation information is the other standards information that can recommend business for i-th question information；The standard information and the recommendation information are sent to the terminal.The embodiment of the present invention further simultaneously discloses a kind of information transmitting apparatus.

Description

A kind of method for sending information and device
Technical field
The present invention relates to commending system technology, more particularly to a kind of method for sending information and device.
Background technology
With continuing to develop for internet, ecommerce is increasingly prevailing, and user is required in major websites daily Browse mass data.The customer service platform of major operators has provided the user answering system, answers user and proposes Every business inquiry and the problem related to operating process.
Existing answering system mainly includes：According to the artificial customer service for being familiar with business for industry is recommended in the inquiry of user Business or commodity；According to user input keyword match technique inquiry matching containing identical vocabulary business or Person's commodity；User is classified, purchase or inquiry focus word according to fellow users are entered to the user Industry business or the recommendation of commodity.
But, although artificial customer service can accurately answer out the problem of user, and it is corresponding to give user Recommendations, but operation cost is too high, and keyword match technique and focus word recommended technology can not be accurately User's business interested is found, answer set substantially can only be returned, reduce the experience of user.
The content of the invention
In order to solve the above technical problems, the embodiment of the present invention is expected to provide a kind of method for sending information and device, Consumer's Experience can be improved while reducing the cost.
The technical proposal of the invention is realized in this way：
First aspect, there is provided a kind of method for sending information, methods described includes：
I-th question information that receiving terminal sends, the i is positive integer；
The corresponding standard information of i-th question information and recommendation information, institute are determined from the first database It is the other standards information that can recommend business for i-th question information to state recommendation information；
The standard information and the recommendation information are sent to the terminal.
Optionally, it is described the corresponding mark information of i-th question information to be determined from the first database and is pushed away The information of recommending includes：
I the first keyword of question information before obtaining；
When first keyword is the keyword of first database, in first database, It is determined that standard information corresponding with first keyword；
According to first keyword, search for relevant with first keyword in first database Multiple standard information；
Determine the output priority of the multiple standard information；
In the multiple standard information, n standard information of output priority highest is determined, the n is Positive integer；
Using described n standard information of output priority highest as the recommendation information.
Optionally, after the transmission recommendation information to the terminal, methods described also includes：
Receive the i+1 question information that the terminal sends；
According to the i+1 question information, first database is updated.
Optionally, the first database also weights including each standard information, described according to the i+1 Individual question information, updating first database includes：
Obtain the second keyword of the i+1 question information；
When second keyword includes the keyword of second database, and the i+1 puts question to letter When not including that receiving user checks the instruction of the n recommendation information in breath, dropped in first database The weight of the low standard information and the n recommendation information；
When second keyword includes the keyword of second database, and the i+1 puts question to letter When breath includes receiving the instruction of the first recommendation information that user is checked in the n recommendation information, institute is improved State the weight of the first recommendation information；
When second keyword does not include the keyword of second database, and the i+1 is putd question to When information includes receiving the instruction of the first recommendation information that user is checked in the n recommendation information, improve The weight of the standard information and first recommendation information；
When second keyword does not include the keyword of second database, and the i+1 is putd question to When not including receiving the instruction of the first recommendation information that user is checked in the n recommendation information in information, carry The weight of the standard information high；
When second keyword is identical with first keyword, reduces the standard information and described push away Recommend the weight of information.
Optionally, the weight for improving first recommendation information includes：
Judge whether second keyword to the path of the standard information；
If there is second keyword to the path of the standard information, delete second keyword and arrive The path of the standard information, improves the weight of first recommendation information；
If in the absence of second keyword to the path of the standard information, second keyword is increased The corresponding upper keyword of the corresponding keyword of the standard information is added, first recommendation information is improved Weight.
Optionally, after the weight for improving the standard information, methods described also includes：
During second keyword increased into the upper keyword of the corresponding keyword of the standard information.
Optionally, it is described when second keyword is identical with first keyword, reduce the standard The weight of information and the recommendation information includes：
When the standard information and the recommendation information can not all answer the question information, the mark is reduced The weight of calibration information and the recommendation information；
When the standard information and the recommendation information are insufficient for the inquiry of user, described first is determined Different keywords in keyword and second keyword；In first database, by the difference Keyword is used as common in the corresponding keyword of the typical problem and the corresponding keyword of the recommendation information Keyword the next keyword.
Optionally, the first database also weights including each standard information, described according to described first Keyword, searches for and the related multiple standard information packages of first keyword in first database Include：
In first database, it is determined that at least one matching path corresponding with first keyword；
According to the matching path, corresponding first standard information in the matching path and first mark are determined The keyword of calibration information；
At least one inquiry road corresponding with the keyword of first standard information is determined in the first database Footpath；
Above-mentioned query process is circulated, untill keyword can not again determine query path position；
The corresponding standard information of query path is looked into as related many with first keyword using what is determined Individual standard information；
The output priority for determining the multiple standard information includes：
Obtain the number of the keyword of each query path；
Obtain the number of times of each query path circulation；
According to the number of times that the number of the keyword of each query path and described each query path are circulated, It is determined that the first serial number of the corresponding standard information of described each query path；
Obtain the weights of the corresponding standard information of described each query path；
By the weights of the corresponding standard information of described each query path, it is determined that described each query path correspondence Standard information the second serial number；
According to first serial number and second serial number of the corresponding standard information of described each query path, It is determined that the output priority of the corresponding standard information of described each query path.
Optionally, the corresponding relation of keyword and service feature of first database also including focus incident； The weights by the corresponding standard information of described each query path, it is determined that described each query path correspondence Standard information the second serial number after, methods described also includes：
When the first focus incident occurs, the 3rd keyword of first focus incident is obtained；
In first database, the corresponding service feature of the 3rd keyword is determined；The business is special Levy is that business uses increased percentage；
Obtain the amount of handling of the business of the business and the user of user；
Business and the corresponding service feature according to the user, determine that the expection of the business of user is used Amount；
The expected usage amount of the business according to the user, determines and the user in first database Business the closest standard information of expected usage amount；
According to the difference of the amount of handling of the expected usage amount and corresponding business of the business of the user, it is determined that described 3rd serial number of closest standard information；
The 3rd serial number, the corresponding mark of described each query path according to the closest standard information First serial number and the second serial number of calibration information, it is determined that have first serial number, the second serial number and The average serial number of the typical problem of the 3rd suitable number；
According to the average serial number, it is determined that with the first serial number, the second serial number and the 3rd along number mark The output priority of calibration information；
Using the standard information with the first serial number and the second serial number as the minimum standard letter of output priority Breath.
Optionally, methods described also includes：
Each focus incident that acquisition occurs in history；
Extract the keyword of each focus incident；
Obtain each business service condition when keyword identical focus incident occurs；
According to described each business service condition, the service feature of the keyword identical focus incident is generated；
The keyword and the corresponding relation of service feature of storage each focus incident.
Second aspect, there is provided a kind of information transmitting apparatus, described device includes：
Receiving unit, for i-th question information that receiving terminal sends, the i is positive integer；
Determining unit, for determining the corresponding standard information of i-th question information from the first database And recommendation information, the recommendation information is the other standards that can recommend business for i-th question information Information；
Transmitting element, for sending the standard information and the recommendation information to the terminal.
Optionally, the determining unit specifically for：
Obtain subelement, the first keyword for obtaining preceding i question information；
Determination subelement, during for being the keyword of first database when first keyword, in institute In stating the first database, it is determined that standard information corresponding with first keyword；
Search subelement, for according to first keyword, searched in first database with it is described The related multiple standard information of first keyword；
The determination subelement, the output priority for determining the multiple standard information；The multiple In standard information, n standard information of output priority highest is determined, the n is positive integer；Will be described N standard information of output priority highest is used as the recommendation information.
Optionally, the receiving unit, is additionally operable to receive the i+1 question information that the terminal sends；
Described device also includes：
Updating block, for according to the i+1 question information, updating first database.
Optionally, the first database also weights including each standard information, the updating block is specific For：
Obtain the second keyword of the i+1 question information；
When second keyword includes the keyword of second database, and the i+1 puts question to letter When not including that receiving user checks the instruction of the n recommendation information in breath, dropped in first database The weight of the low standard information and the n recommendation information；
When second keyword includes the keyword of second database, and the i+1 puts question to letter When breath includes receiving the instruction of the first recommendation information that user is checked in the n recommendation information, institute is improved State the weight of the first recommendation information；
When second keyword does not include the keyword of second database, and the i+1 is putd question to When information includes receiving the instruction of the first recommendation information that user is checked in the n recommendation information, improve The weight of the standard information and first recommendation information；
When second keyword does not include the keyword of second database, and the i+1 is putd question to When not including receiving the instruction of the first recommendation information that user is checked in the n recommendation information in information, carry The weight of the standard information high；
When second keyword is identical with first keyword, reduces the standard information and described push away Recommend the weight of information.
Optionally, the updating block is additionally operable to：
Judge whether second keyword to the path of the standard information；
If there is second keyword to the path of the standard information, delete second keyword and arrive The path of the standard information, improves the weight of first recommendation information；
If in the absence of second keyword to the path of the standard information, second keyword is increased The corresponding upper keyword of the corresponding keyword of the standard information is added, first recommendation information is improved Weight.
Optionally, described device also includes：
Processing unit, for second keyword to be increased into the corresponding keyword of the standard information In the keyword of position.
Optionally, the updating block is additionally operable to：
When the standard information and the recommendation information can not all answer the question information, the mark is reduced The weight of calibration information and the recommendation information；
When the standard information and the recommendation information are insufficient for the inquiry of user, described first is determined Different keywords in keyword and second keyword；In first database, by the difference Keyword is used as common in the corresponding keyword of the typical problem and the corresponding keyword of the recommendation information Keyword the next keyword.
Optionally, the first database also weights including each standard information, the search subelement tool Body is used for：
In first database, it is determined that at least one matching path corresponding with first keyword；
According to the matching path, corresponding first standard information in the matching path and first mark are determined The keyword of calibration information；
At least one inquiry road corresponding with the keyword of first standard information is determined in the first database Footpath；
Above-mentioned query process is circulated, untill keyword can not again determine query path position；
The corresponding standard information of query path is looked into as related many with first keyword using what is determined Individual standard information；
The determination subelement specifically for：
Obtain the number of the keyword of each query path；
Obtain the number of times of each query path circulation；
According to the number of times that the number of the keyword of each query path and described each query path are circulated, It is determined that the first serial number of the corresponding standard information of described each query path；
Obtain the weights of the corresponding standard information of described each query path；
By the weights of the corresponding standard information of described each query path, it is determined that described each query path correspondence Standard information the second serial number；
According to first serial number and second serial number of the corresponding standard information of described each query path, It is determined that the output priority of the corresponding standard information of described each query path.
Optionally, the corresponding relation of keyword and service feature of first database also including focus incident； Described device also includes：
Acquiring unit, the 3rd pass for when the first focus incident occurs, obtaining first focus incident Keyword；Obtain the amount of handling of the business of the business and the user of user；
The determining unit is additionally operable in first database, determines the corresponding industry of the 3rd keyword Business feature；The service feature is that business uses increased percentage；Business according to the user and described Corresponding service feature, determines the expected usage amount of the business of user；The expection of the business according to the user Usage amount, determines closest with the expected usage amount of the business of the user in first database Standard information；According to the difference of the amount of handling of the expected usage amount and corresponding business of the business of the user, really 3rd serial number of the fixed closest standard information；According to the of the closest standard information First serial number and the second serial number of three serial numbers, the corresponding standard information of described each query path, really Surely there is the average serial number of first serial number, the second serial number and the typical problem of the 3rd suitable number；Press According to the average serial number, it is determined that with the first serial number, the second serial number and the 3rd along number standard information Output priority；Using the standard information with the first serial number and the second serial number as output priority most Low standard information.
Optionally, the acquiring unit is additionally operable to obtain each focus incident for occurring in history；Obtain described The keyword of each focus incident；Obtain each business service condition when keyword identical focus incident occurs；
Described device also includes：
Generation unit, for according to described each business service condition, generating the keyword identical focus The service feature of event；
Memory cell, keyword and the corresponding relation of service feature for storing each focus incident. The embodiment of the invention provides a kind of method for sending information and device, i-th enquirement that first receiving terminal sends Information；Further according to i-th question information, the corresponding standard of i-th question information is determined from the first database Information and recommendation information, the recommendation information be can be i-th question information recommend business other Standard information；Afterwards, standard information and recommendation information are sent to terminal.So, sent for terminal User put question to (question information), can not only provide standard information, recommendation information can also be given, this Sample, even if standard information is not user puts question to corresponding correct option, recommendation information is also likely to be correct option, Therefore, the satisfaction of user is increased, Consumer's Experience is improve, meanwhile, either recommendation information is still marked Calibration information is all the information for automatically replying, from artificial operation, therefore, save cost of labor.
Brief description of the drawings
Fig. 1 is a kind of flow chart of method for sending information provided in an embodiment of the present invention；
Fig. 2 is the flow chart of another method for sending information provided in an embodiment of the present invention；
Fig. 3 is a kind of schematic diagram of information transmitting apparatus provided in an embodiment of the present invention；
Fig. 4 is the schematic diagram of another information transmitting apparatus provided in an embodiment of the present invention；
Fig. 5 is the schematic diagram of another information transmitting apparatus provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clearly Chu, it is fully described by.
Embodiment one
The embodiment of the present invention provides a kind of method for sending information, is applied to information transmitting apparatus, and the information sends Device can be the portion of server.As shown in figure 1, the method includes：
I-th question information that step 101, receiving terminal send.
Here, i is positive integer, and question information is the sentence that user is used for consultation service or commodity, such as " I Credit balance be how many”；It can also be negative emotions sentence to put question to sentence, for example, " too bad ", " complete Do not use entirely " etc..
Step 102, according to i-th question information, i-th question information correspondence is determined from the first database Standard information and recommendation information.
Here, recommendation information is the other standards information that can recommend business for i-th question information； First database purchase standard information, keyword and its corresponding path.
Specifically, i the first keyword of question information before obtaining；When the first keyword is the first database Keyword when, in the first database, it is determined that standard information corresponding with the first keyword；According to first Keyword, search and the related multiple standard information of the first keyword in the first database；It is determined that multiple The output priority of standard information；In multiple standard information, n standard of output priority highest is determined Information, the n is positive integer；Using n standard information of output priority highest as the recommendation information. Here, the first database is included not only including keyword, also including the semantic relation between keyword.Such as, " set meal " this keyword has many subservices, e.g., " flying to enjoy set meal ", " travelling merchants' set meal ", " free set meal " And " online set meal ".So in knowledge base, behind this pass of this four business keywords and " set meal " Keyword is exactly the semantic the next relation upper with semanteme, and semantic hyponymy can be " upper with triple Word "-" being divided into "-" hyponym " is represented.That is " set meal " is upper keyword, " flies to enjoy set Meal ", " travelling merchants' set meal ", " free set meal " and " online set meal " are the next keywords of " set meal ". Therefore, there is such the next semantic relation between all of keyword.
What deserves to be explained is, because there are many business in each province, if only the key according to user's query Word matching carries out business recommended to user, it is easy to cause the recommendation of redundancy.For example, if user askes The keyword asked is " how handling travelling merchants' set meal ", only according to the mode of Keywords matching, corresponding standard letter Breath has：" introduction of 4G set meals ", " cancel 4G set meals ", " introduction of 4G travelling merchants' set meal ", " open 4G travelling merchants Set meal " etc..And the triple in by the first database is to carry out Keywords matching, business Logical relation standard information farther out, e.g., " introduction of 4G set meals " and " cancelling 4G set meals " will be by mistake Filter, leave behind " introduction of 4G travelling merchants' set meal " and " opening 4G travelling merchants' set meal " this service logic relation Close standard information.
Further, the first database also weights including each standard information, described to be closed according to described first Keyword, searched in first database includes with the related multiple standard information of first keyword： In first database, it is determined that at least one matching path corresponding with first keyword；According to The matching path, determines corresponding first standard information in the matching path and first standard information Keyword；Determine to be looked into the keyword corresponding at least one of first standard information in the first database Ask path；Above-mentioned query process is circulated, untill keyword can not again determine query path position；Will be true The corresponding standard information of query path of looking into made is believed as with the related multiple standards of first keyword Breath.Here, searching each accessed path related to first keyword can include：In the first data In storehouse, matching path is matched according to markup information, following inquiry is done again to each matching path：Constantly The Section 1 accessed path with the matching path as the triple of Section 3 element is found, then is found with Section 1 Accessed path as the triple of Section 3 accessed path Section 1 accessed path, limit this process, directly To no triple can be inquired about, all paths in search procedure are recorded, also to record each The triple number keyword number corresponding with each accessed path that path includes；Wherein, triple is individual Number is exactly the cycle-index of each query path.
Further, the output priority for determining the multiple standard information includes：Obtain it is described each The number of the keyword of query path；Obtain the number of times of each query path circulation；According to it is described each The number of the keyword of query path and the number of times of described each query path circulation, it is determined that described each inquiry First serial number of the corresponding standard information in path；Obtain the corresponding standard information of described each query path Weights；By the weights of the corresponding standard information of described each query path, it is determined that described each query path pair Second serial number of the standard information answered；According to the corresponding standard information of described each query path first is suitable Sequence number and second serial number, it is determined that the output priority of the corresponding standard information of described each query path. Here, the number of times of query path circulation refers to each cyclic query, Zhi Daozai from the query path Cycle-index during query path can not be inquired；The number of the keyword is more, query path circulation time First serial number of the more standard information of number is smaller, conversely, the first serial number of standard information is bigger； The bigger standard information of weights, its second serial number is smaller.
The corresponding relation of keyword and service feature of first database also including focus incident；It is described to press The weights of the corresponding standard information of each query path, determine the of the corresponding standard information of each query path After two serial numbers, methods described also includes：When the first focus incident occurs, the first focus incident is obtained The 3rd keyword；In the first database, the corresponding service feature of the 3rd keyword is determined；The business It is characterized in that business uses increased percentage；Obtain the amount of handling of the business of the business and the user of user； Business and the corresponding service feature according to the user, determine the expected usage amount of the business of user； The expected usage amount of the business according to the user, determines the industry with the user in first database The closest standard information of the expected usage amount of business；According to the expected usage amount of the business of the user and right The difference of the amount of handling of the business answered, determines the 3rd serial number of the closest standard information；According to institute State the 3rd serial number, the of the corresponding standard information of described each query path of closest standard information One serial number and the second serial number, it is determined that with first serial number, the second serial number and the 3rd along number The average serial number of typical problem；According to the average serial number, it is determined that having the first serial number, second suitable The output priority of sequence number and the standard information of the 3rd suitable number；To there is the first serial number and the second serial number Standard information is used as the minimum standard information of output priority.
Step 103, to terminal send standard information and recommendation information.
After step 103, methods described also includes：The i+1 question information that receiving terminal sends； According to i+1 question information, the first database is updated.
Further, the first database also weights including each standard information, it is described according to described the I+1 question information, updates first database and specifically includes：Obtain the second of i+1 question information Keyword；When the second keyword includes the keyword of the second database, and do not wrapped in i+1 question information Include when receiving user and checking the instruction of n recommendation information, the information that debased the standard in the first database and n are individual The weight of recommendation information；When the second keyword includes the keyword of the second database, and i+1 puts question to letter When breath includes receiving the instruction of the first recommendation information that user is checked in n recommendation information, improve first and push away Recommend the weight of information；When the second keyword does not include the keyword of the second database, and i+1 puts question to letter When breath includes receiving the instruction of the first recommendation information that user is checked in n recommendation information, standard letter is improved The weight of breath and the first recommendation information；When the second keyword does not include the keyword of the second database, and i+1 When not including receiving the instruction of the first recommendation information that user is checked in n recommendation information in individual question information, Improve the weight of standard information；When the second keyword is identical with the first keyword, the information that debases the standard and push away Recommend the weight of information.
Further, the weight for improving first recommendation information includes：Judge whether described Two keywords are to the path of the standard information；If there is second keyword to the road of the standard information Footpath, then delete second keyword to the path of the standard information, improves first recommendation information Weight；If in the absence of second keyword to the path of the standard information, by second keyword The corresponding keyword of the standard information is added to, the weight of first recommendation information is improved.
Further, after the weight for improving the standard information, methods described also includes：Will be described Second keyword increases in the upper keyword of the corresponding keyword of the standard information.
Further, it is described when the first keyword is identical with second keyword, the information that debases the standard and The weight of recommendation information includes：Believe when the standard information and the recommendation information can not all answer described enquirement During breath, the weight of the standard information and the recommendation information is reduced；When the standard information and the recommendation When information is insufficient for the inquiry of user, determine in first keyword and second keyword not Same keyword；In first database, using the different keywords as in typical problem correspondence Keyword and the corresponding keyword of the recommendation information in common keyword the next keyword.Here, The i+1 question information of the input of user is parsed, analytically result just can determine standard information With the problem whether recommendation information answers question information；Or whether partly answer the problem of question information.
Further, methods described also includes：Each focus incident that acquisition occurs in history；Obtain described The keyword of each focus incident；Obtain each business service condition when keyword identical focus incident occurs； According to described each business service condition, the service feature of the keyword identical focus incident is generated；Deposit The keyword and the corresponding relation of service feature of storage each focus incident.
So, (question information) is putd question to for the user that terminal sends, can not only provides standard letter Breath, can also provide recommendation information, so, even if standard information is not user puts question to corresponding correct option, Recommendation information is also likely to be correct option, therefore, the satisfaction of user is increased, Consumer's Experience is improve, Meanwhile, either recommendation information or standard information are all the information for automatically replying, and are operated from artificial, because This, has saved cost of labor.
Embodiment two
The embodiment of the present invention provides a kind of method for sending information, and the method is applied to network automatic answering system, The system includes the terminal and server for communicating, as shown in Fig. 2 the present embodiment station is entered in server side Row is introduced, and the method includes：
I-th question information that step 201, receiving terminal send.
Here, i is positive integer.
Step 202, at least one first keywords of acquisition from i-th question information.
For example, question information is " to could you tell me, my data traffic also remains how many", what server was obtained Keyword is exactly " data traffic ", " surplus " and " how many "；Question information can also be " completely useless ", The first keyword that server is obtained is " useless ".
Step 203, when the first keyword of i-th question information is the keyword of the first database, obtain The keyword of preceding i-1 question information.
Specifically, knowledge base can include at least two databases, the first database purchase keyword, standard Information and its path relation, the keyword of the second database purchase negative emotions, such as " wrong ", " completely It is useless ".What deserves to be explained is, when the first keyword had both been not belonging to the first database or had been not belonging to the second database, First keyword is equivalent to be do not occur.
Step 204, the keyword according to preceding i question information, determine that i-th enquirement is believed from knowledge base Cease corresponding standard information.
Step 205, the keyword according to preceding i question information, determine i-th from knowledge base and push away literary letter Cease corresponding recommendation information.
Specifically, obtaining the multiple roads corresponding with the keyword of preceding i question information from the first database Footpath relation, by taking one of path relation as an example, in the path relation, determines and the path relation phase All keywords of association, the triple number of the path relation, specifically, being done to each path relation The inquiry of following relation：Constantly look for the Section 1 path with path relation as the triple of Section 3 element Relation, then find the Section 1 using Section 1 path relation as next triple of Section 3 path relation Path relation, limit this process, untill no triple can be inquired about, in recording search procedure All paths, also to record the triple number that each path includes, accordingly, determine each path Relation is corresponding to be ranked up to path relation, by the path that keyword number is more and triple number is more Sequence is more forward, First ray is obtained, by corresponding standard information group in each path relation in First ray One standard information set of synthesis；Standard information is ranked up according to their existing weights, second is obtained Sequence；The increase ratio of the business being inferred to according to default focus incident, according to the corresponding user of terminal The business handled, determines all of recommendable business and actual increase ratio, generates recommendable business Corresponding standard information set, obtains according to the increase ratio in each standard information and the actual difference for increasing ratio Value sorts from big to small, obtains the 3rd sequence；By the standard in First ray, the second sequence and the 3rd sequence The sequence number of information averagely, by the size of average value, standard information is sorted, and by first five standard Information as recommendation information is sent to terminal.
Here, above-mentioned query process is the equal of the upper path for searching the path relation, until finding most Upper path relation.For example, the upper path layer of " 4G flies young business " is for " 4G business " and " flies Young business ", the upper path layer of " flying young business " is " business of M-ZONE campus industry ", " dynamic The upper path layer of sense area campus industry business " is " M-ZONE business ".It is somebody's turn to do " 4G flies young business " The level in upper path be 4 layers, that is, the number of triple is 4.
Step 206, the corresponding standard information of i-th question information and recommendation information are sent to terminal.
Here, standard information and recommendation information can be sent in the form of audio, it is also possible to word example Form such as short message sends.The standard information and recommendation information of the present embodiment are sent in the way of short message To terminal.
The i+1 question information that step 207, receiving terminal send.
Step 208, from i+1 question information extract keyword.
Step 209, it is the keyword of the first database when the keyword of i+1 question information, and does not receive When user clicks on recommendation information, the weight of i-th standard information and recommendation information is reduced.Terminate this flow.
Here, it can not receive user's click in the scheduled time to push away not receive user and click on recommendation information Recommend the operation of information, the i-th+2 question informations that receiving terminal sends or terminal and communicate three with server stopping The situation of kind.
Step 210, it is the keyword of the first database when the keyword of i+1 question information, and receives When user clicks on the operation of recommendation information, the keyword of i-th question information and the path of standard information are judged Relation whether there is.If in the presence of execution step 210；If not existing, step 211 is performed.
The path relation of step 211, the keyword of i-th question information of deletion and standard information, increases by i-th The weight of the recommendation information of individual question information.Terminate this flow.
Step 212, i-th weight of the recommendation information of question information of increase.
Step 213, that the keyword of i-th question information is added to the corresponding keyword of standard information is corresponding In upper keyword, terminate this flow.
Step 214, when the keyword of i+1 question information be not the pass of the first database or the second database Keyword, and when receiving the operation of user's click recommendation information, increase by i-th recommendation information of question information With the weight of standard information, terminate this flow.
Step 215, when the keyword of i+1 question information be not the pass of the first database or the second database Keyword, and when not receiving the operation of user's click recommendation information, increase by i-th standard letter of question information The weight of breath, increases by i-th upper keyword of the keyword of question information.
Specifically, the upper keyword for increasing by i-th keyword of question information includes：Obtain i-th enquirement The corresponding keyword of standard information of information, deletes the pass being not stored in the second database in standard keyword Keyword, during the keyword of i-th question information to replenish the upper keyword of keyword.
Here, keyword is the stem content in standard information, for example：Standard information is that " voice inquirement is provided Take ", keyword is respectively " inquiry ", " voice " and " rate ".Due to the number stored in the second database According to being mostly colloquial keyword, that is, user's frequency of use keyword higher, and standard key During word is not frequently used, such as corresponding colloquial keyword of standard keyword " rate " is " telephone expenses ". Seldom someone will use " rate ", what majority can use is " telephone expenses ".Therefore, deletion is this kind of does not make usually Standard keyword, saves on the space internal memory of the second database.
What deserves to be explained is, the keyword in the present embodiment is a point hyponymy.
Embodiment three
The embodiment of the present invention provides a kind of information transmitting apparatus 30, as shown in figure 3, the device 30 includes：
Receiving unit 301, for i-th question information that receiving terminal sends, the i is positive integer.
Determining unit 302, for determining the corresponding standard letter of i-th question information from the first database Breath and recommendation information, the recommendation information are other marks that can recommend business for i-th question information Calibration information.
Transmitting element 303, for sending the standard information and the recommendation information to the terminal.
So, (question information) is putd question to for the user that terminal sends, can not only provides standard letter Breath, can also provide recommendation information, so, even if standard information is not user puts question to corresponding correct option, Recommendation information is also likely to be correct option, therefore, the satisfaction of user is increased, Consumer's Experience is improve, Meanwhile, either recommendation information or standard information are all the information for automatically replying, and are operated from artificial, because This, has saved cost of labor.
Further, as shown in figure 4, the determining unit 302 specifically for：
Obtain subelement 3021, the first keyword for obtaining preceding i question information；
Determination subelement 3022, in first database, it is determined that corresponding with first keyword Standard information；
Search subelement 3023, for according to first keyword, in first database search with The related multiple standard information of first keyword；
The determination subelement 3022, the output priority for determining the multiple standard information；Described In multiple standard information, n standard information of output priority highest is determined, the n is positive integer；Will Described n standard information of output priority highest is used as the recommendation information.
Further, the receiving unit 301 is additionally operable to receive the i+1 enquirement letter that the terminal sends Breath；
As shown in figure 5, described device 30 also includes：
Updating block 304, for according to the i+1 question information, updating first database.
Further, first the database also weights including each standard information, the updating block 304 Specifically for：
Obtain the second keyword of the i+1 question information；
When second keyword includes the keyword of second database, and the i+1 puts question to letter When not including that receiving user checks the instruction of the n recommendation information in breath, dropped in first database The weight of the low standard information and the n recommendation information；
When second keyword includes the keyword of second database, and the i+1 puts question to letter When breath includes receiving the instruction of the first recommendation information that user is checked in the n recommendation information, institute is improved State the weight of the first recommendation information；
When second keyword does not include the keyword of second database, and the i+1 is putd question to When information includes receiving the instruction of the first recommendation information that user is checked in the n recommendation information, improve The weight of the standard information and first recommendation information；
When second keyword does not include the keyword of second database, and the i+1 is putd question to When not including receiving the instruction of the first recommendation information that user is checked in the n recommendation information in information, carry The weight of the standard information high；
When second keyword is identical with first keyword, reduces the standard information and described push away Recommend the weight of information.
Further, the updating block 304 is additionally operable to：
Judge whether second keyword to the path of the standard information；
If there is second keyword to the path of the standard information, delete second keyword and arrive The path of the standard information, improves the weight of first recommendation information；
If in the absence of second keyword to the path of the standard information, second keyword is increased The corresponding keyword of the standard information is added, the weight of first recommendation information is improved.
Further, as shown in figure 5, described device 30 also includes：
Processing unit 305, for second keyword to be increased into the corresponding keyword of the standard information Upper keyword in.
Further, the updating block 304 is additionally operable to：
When the standard information and the recommendation information can not all answer the question information, the mark is reduced The weight of calibration information and the recommendation information；
When the standard information and the recommendation information are insufficient for the inquiry of user, described first is determined Different keywords in keyword and second keyword；In first database, by the difference Keyword is splitted out from the corresponding keyword of the typical problem and the corresponding keyword of the recommendation information.
Further, first the database also weights including each standard information, the search subelement 3023 specifically for：
In first database, it is determined that at least one matching path corresponding with first keyword；
According to the matching path, corresponding first standard information in the matching path and first mark are determined The keyword of calibration information；
At least one inquiry road corresponding with the keyword of first standard information is determined in the first database Footpath；
Above-mentioned query process is circulated, untill keyword can not again determine query path position；
The corresponding standard information of query path is looked into as related many with first keyword using what is determined Individual standard information；
The determination subelement 3022 specifically for：
Obtain the number of the keyword of each query path；
Obtain the number of times of each query path circulation；
According to the number of times that the number of the keyword of each query path and described each query path are circulated, It is determined that the first serial number of the corresponding standard information of described each query path；
Obtain the weights of the corresponding standard information of described each query path；
By the weights of the corresponding standard information of described each query path, it is determined that described each query path correspondence Standard information the second serial number；
According to first serial number and second serial number of the corresponding standard information of described each query path, It is determined that the output priority of the corresponding standard information of described each query path.
Further, the correspondence pass of keyword and service feature of first database also including focus incident System；As shown in figure 5, described device 30 also includes：
Acquiring unit 306, for when the first focus incident occurs, obtains the of first focus incident Three keywords；Obtain the business of user；
The determining unit 302 is additionally operable in first database, determines the 3rd keyword correspondence Service feature；The service feature is that business uses increased percentage；Business according to the user and The corresponding service feature, determines the expected usage amount of the business of user；Business according to the user Expected usage amount, determines to be connect the most with the expected usage amount of the business of the user in first database Near standard information；According to the difference of the amount of handling of the expected usage amount and corresponding business of the business of the user, Determine the 3rd serial number of the closest standard information；According to the closest standard information First serial number and the second serial number of the 3rd serial number, the corresponding standard information of described each query path, It is determined that with first serial number, the second serial number and the 3rd along number typical problem average serial number； According to the average serial number, it is determined that with the first serial number, the second serial number and the 3rd along number standard letter The output priority of breath；Using the standard information with the first serial number and the second serial number as output priority Minimum standard information.
Further, the acquiring unit 306 is additionally operable to obtain each focus incident for occurring in history；Obtain Take the keyword of each focus incident；Obtaining each business when keyword identical focus incident occurs makes Use situation；As shown in figure 5, described device 30 also includes：
Generation unit 307, for according to described each business service condition, generating the keyword identical The service feature of focus incident；
Memory cell 308, the correspondence of keyword and service feature for storing each focus incident is closed System.
In actual applications, the receiving unit 301, determining unit 302, transmitting element 303, renewal are single Unit 304, processing unit 305, acquiring unit 306, generation unit 307 and memory cell 308 can be by positions Central processing unit (Central Processing Unit, CPU) in information transmitting apparatus 30, microprocessor (Micro Processor Unit, MPU), digital signal processor (Digital Signal Processor, DSP), Or field programmable gate array (Field Programmable Gate Array, FPGA) etc. is realized.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, system or meter Calculation machine program product.Therefore, the present invention can using hardware embodiment, software implementation or combine software and The form of the embodiment of hardware aspect.And, the present invention can be used and wherein include calculating at one or more Computer-usable storage medium (the including but not limited to magnetic disk storage and optical storage of machine usable program code Device etc.) on implement computer program product form.
The present invention is with reference to method according to embodiments of the present invention, equipment (system) and computer program product Flow chart and/or block diagram describe.It should be understood that flow chart and/or side can be realized by computer program instructions The knot of flow in each flow and/or square frame and flow chart and/or block diagram and/or square frame in block diagram Close.Can provide these computer program instructions to all-purpose computer, special-purpose computer, Embedded Processor or The processor of other programmable data processing devices is producing a machine so that by computer or other can The instruction of the computing device of programming data processing equipment is produced for realizing in one flow of flow chart or multiple The device of the function of being specified in one square frame of flow and/or block diagram or multiple square frames.
These computer program instructions may be alternatively stored in can guide computer or other programmable data processing devices In the computer-readable memory for working in a specific way so that storage is in the computer-readable memory Instruction is produced includes the manufacture of command device, and the command device is realized in one flow of flow chart or multiple streams The function of being specified in one square frame of journey and/or block diagram or multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices, made Obtain and series of operation steps performed on computer or other programmable devices to produce computer implemented treatment, So as to the instruction performed on computer or other programmable devices is provided for realizing in one flow of flow chart Or specified in multiple one square frame of flow and/or block diagram or multiple square frames function the step of.
The above, only presently preferred embodiments of the present invention is not intended to limit protection model of the invention Enclose.

Claims (20)

1. a kind of method for sending information, it is characterised in that methods described includes：
I-th question information that receiving terminal sends, the i is positive integer；
The corresponding standard information of i-th question information and recommendation information, institute are determined from the first database It is the other standards information that can recommend business for i-th question information to state recommendation information；
The standard information and the recommendation information are sent to the terminal.
2. method according to claim 1, it is characterised in that described that institute is determined from the first database Stating the corresponding mark information of i-th question information and recommendation information includes：
I the first keyword of question information before obtaining；
When first keyword is the keyword of first database, in first database, It is determined that standard information corresponding with first keyword；
According to first keyword, search for relevant with first keyword in first database Multiple standard information；
Determine the output priority of the multiple standard information；
In the multiple standard information, n standard information of output priority highest is determined, the n is Positive integer；
Using described n standard information of output priority highest as the recommendation information.
3. method according to claim 1, it is characterised in that it is described to the terminal send described in push away Recommend after information, methods described also includes：
Receive the i+1 question information that the terminal sends；
According to the i+1 question information, first database is updated.
4. method according to claim 3, it is characterised in that first database also includes each The weights of standard information, described according to the i+1 question information, updating first database includes：
Obtain the second keyword of the i+1 question information；
When second keyword includes the keyword of second database, and the i+1 puts question to letter When not including that receiving user checks the instruction of the n recommendation information in breath, dropped in first database The weight of the low standard information and the n recommendation information；
When second keyword includes the keyword of second database, and the i+1 puts question to letter When breath includes receiving the instruction of the first recommendation information that user is checked in the n recommendation information, institute is improved State the weight of the first recommendation information；
When second keyword does not include the keyword of second database, and the i+1 is putd question to When information includes receiving the instruction of the first recommendation information that user is checked in the n recommendation information, improve The weight of the standard information and first recommendation information；
When second keyword does not include the keyword of second database, and the i+1 is putd question to When not including receiving the instruction of the first recommendation information that user is checked in the n recommendation information in information, carry The weight of the standard information high；
When second keyword is identical with first keyword, reduces the standard information and described push away Recommend the weight of information.
5. method according to claim 4, it is characterised in that raising first recommendation information Weight include：
Judge whether second keyword to the path of the standard information；
If there is second keyword to the path of the standard information, delete second keyword and arrive The path of the standard information, improves the weight of first recommendation information；
If in the absence of second keyword to the path of the standard information, second keyword is increased The corresponding upper keyword of the corresponding keyword of the standard information is added, first recommendation information is improved Weight.
6. method according to claim 4, it is characterised in that the power of the raising standard information After weight, methods described also includes：
During second keyword increased into the upper keyword of the corresponding keyword of the standard information.
7. method according to claim 4, it is characterised in that described when second keyword and institute State the first keyword it is identical when, the weight for reducing the standard information and the recommendation information includes：
When the standard information and the recommendation information can not all answer the question information, the mark is reduced The weight of calibration information and the recommendation information；
When the standard information and the recommendation information are insufficient for the inquiry of user, described first is determined Different keywords in keyword and second keyword；In first database, by the difference Keyword is used as common in the corresponding keyword of the typical problem and the corresponding keyword of the recommendation information Keyword the next keyword.
8. method according to claim 2, it is characterised in that first database also includes each The weights of standard information, it is described according to first keyword, searched in first database with it is described The related multiple standard information of first keyword include：
In first database, it is determined that at least one matching path corresponding with first keyword；
According to the matching path, corresponding first standard information in the matching path and first mark are determined The keyword of calibration information；
At least one inquiry road corresponding with the keyword of first standard information is determined in the first database Footpath；
Above-mentioned query process is circulated, untill keyword can not again determine query path position；
The corresponding standard information of query path is looked into as related many with first keyword using what is determined Individual standard information；
The output priority for determining the multiple standard information includes：
Obtain the number of the keyword of each query path；
Obtain the number of times of each query path circulation；
According to the number of times that the number of the keyword of each query path and described each query path are circulated, It is determined that the first serial number of the corresponding standard information of described each query path；
Obtain the weights of the corresponding standard information of described each query path；
By the weights of the corresponding standard information of described each query path, it is determined that described each query path correspondence Standard information the second serial number；
According to first serial number and second serial number of the corresponding standard information of described each query path, It is determined that the output priority of the corresponding standard information of described each query path.
9. method according to claim 8, it is characterised in that first database also includes focus The keyword of event and the corresponding relation of service feature；It is described to believe by the corresponding standard of described each query path The weights of breath, it is determined that after the second serial number of the corresponding standard information of described each query path, the side Method also includes：
When the first focus incident occurs, the 3rd keyword of first focus incident is obtained；
In first database, the corresponding service feature of the 3rd keyword is determined；The business is special Levy is that business uses increased percentage；
Obtain the amount of handling of the business of the business and the user of user；
Business and the corresponding service feature according to the user, determine that the expection of the business of user is used Amount；
The expected usage amount of the business according to the user, determines and the user in first database Business the closest standard information of expected usage amount；
According to the difference of the amount of handling of the expected usage amount and corresponding business of the business of the user, it is determined that described 3rd serial number of closest standard information；
The 3rd serial number, the corresponding mark of described each query path according to the closest standard information First serial number and the second serial number of calibration information, it is determined that have first serial number, the second serial number and The average serial number of the typical problem of the 3rd suitable number；
According to the average serial number, it is determined that with the first serial number, the second serial number and the 3rd along number mark The output priority of calibration information；
Using the standard information with the first serial number and the second serial number as the minimum standard letter of output priority Breath.
10. method according to claim 9, it is characterised in that methods described also includes：
Each focus incident that acquisition occurs in history；
Extract the keyword of each focus incident；
Obtain each business service condition when keyword identical focus incident occurs；
According to described each business service condition, the service feature of the keyword identical focus incident is generated；
The keyword and the corresponding relation of service feature of storage each focus incident.
11. a kind of information transmitting apparatus, it is characterised in that described device includes：
Receiving unit, for i-th question information that receiving terminal sends, the i is positive integer；
Determining unit, for determining the corresponding standard information of i-th question information from the first database And recommendation information, the recommendation information is the other standards that can recommend business for i-th question information Information；
Transmitting element, for sending the standard information and the recommendation information to the terminal.
12. devices according to claim 11, it is characterised in that the determining unit specifically for：
Obtain subelement, the first keyword for obtaining preceding i question information；
Determination subelement, during for being the keyword of first database when first keyword, in institute In stating the first database, it is determined that standard information corresponding with first keyword；
Search subelement, for according to first keyword, searched in first database with it is described The related multiple standard information of first keyword；
The determination subelement, the output priority for determining the multiple standard information；The multiple In standard information, n standard information of output priority highest is determined, the n is positive integer；Will be described N standard information of output priority highest is used as the recommendation information.
13. devices according to claim 11, it is characterised in that the receiving unit, are additionally operable to connect Receive the i+1 question information that the terminal sends；
Described device also includes：
Updating block, for according to the i+1 question information, updating first database.
14. devices according to claim 13, it is characterised in that first database also includes each The weights of individual standard information, the updating block specifically for：
Obtain the second keyword of the i+1 question information；
When second keyword includes the keyword of second database, and the i+1 puts question to letter When not including that receiving user checks the instruction of the n recommendation information in breath, dropped in first database The weight of the low standard information and the n recommendation information；
When second keyword includes the keyword of second database, and the i+1 puts question to letter When breath includes receiving the instruction of the first recommendation information that user is checked in the n recommendation information, institute is improved State the weight of the first recommendation information；
When second keyword does not include the keyword of second database, and the i+1 is putd question to When information includes receiving the instruction of the first recommendation information that user is checked in the n recommendation information, improve The weight of the standard information and first recommendation information；
When second keyword does not include the keyword of second database, and the i+1 is putd question to When not including receiving the instruction of the first recommendation information that user is checked in the n recommendation information in information, carry The weight of the standard information high；
When second keyword is identical with first keyword, reduces the standard information and described push away Recommend the weight of information.
15. devices according to claim 14, it is characterised in that the updating block is additionally operable to：
Judge whether second keyword to the path of the standard information；
If there is second keyword to the path of the standard information, delete second keyword and arrive The path of the standard information, improves the weight of first recommendation information；
If in the absence of second keyword to the path of the standard information, second keyword is increased The corresponding upper keyword of the corresponding keyword of the standard information is added, first recommendation information is improved Weight.
16. devices according to claim 14, it is characterised in that described device also includes：
Processing unit, for second keyword to be increased into the corresponding keyword of the standard information In the keyword of position.
17. devices according to claim 14, it is characterised in that the updating block is additionally operable to：
When the standard information and the recommendation information can not all answer the question information, the mark is reduced The weight of calibration information and the recommendation information；
When the standard information and the recommendation information are insufficient for the inquiry of user, described first is determined Different keywords in keyword and second keyword；In first database, by the difference Keyword is used as common in the corresponding keyword of the typical problem and the corresponding keyword of the recommendation information Keyword the next keyword.
18. devices according to claim 12, it is characterised in that first database also includes each The weights of individual standard information, the search subelement specifically for：
In first database, it is determined that at least one matching path corresponding with first keyword；
According to the matching path, corresponding first standard information in the matching path and first mark are determined The keyword of calibration information；
At least one inquiry road corresponding with the keyword of first standard information is determined in the first database Footpath；
Above-mentioned query process is circulated, untill keyword can not again determine query path position；
The corresponding standard information of query path is looked into as related many with first keyword using what is determined Individual standard information；
The determination subelement specifically for：
Obtain the number of the keyword of each query path；
Obtain the number of times of each query path circulation；
According to the number of times that the number of the keyword of each query path and described each query path are circulated, It is determined that the first serial number of the corresponding standard information of described each query path；
Obtain the weights of the corresponding standard information of described each query path；
By the weights of the corresponding standard information of described each query path, it is determined that described each query path correspondence Standard information the second serial number；
According to first serial number and second serial number of the corresponding standard information of described each query path, It is determined that the output priority of the corresponding standard information of described each query path.
19. devices according to claim 18, it is characterised in that first database also includes heat The keyword of point event and the corresponding relation of service feature；Described device also includes：
Acquiring unit, the 3rd pass for when the first focus incident occurs, obtaining first focus incident Keyword；Obtain the amount of handling of the business of the business and the user of user；
The determining unit is additionally operable in first database, determines the corresponding industry of the 3rd keyword Business feature；The service feature is that business uses increased percentage；Business according to the user and described Corresponding service feature, determines the expected usage amount of the business of user；The expection of the business according to the user Usage amount, determines closest with the expected usage amount of the business of the user in first database Standard information；According to the difference of the amount of handling of the expected usage amount and corresponding business of the business of the user, really 3rd serial number of the fixed closest standard information；According to the of the closest standard information First serial number and the second serial number of three serial numbers, the corresponding standard information of described each query path, really Surely there is the average serial number of first serial number, the second serial number and the typical problem of the 3rd suitable number；Press According to the average serial number, it is determined that with the first serial number, the second serial number and the 3rd along number standard information Output priority；Using the standard information with the first serial number and the second serial number as output priority most Low standard information.
20. methods according to claim 19, it is characterised in that
The acquiring unit is additionally operable to obtain each focus incident for occurring in history；Obtain described each focus The keyword of event；Obtain each business service condition when keyword identical focus incident occurs；
Described device also includes：
Generation unit, for according to described each business service condition, generating the keyword identical focus The service feature of event；
Memory cell, keyword and the corresponding relation of service feature for storing each focus incident.
CN201511020894.1A 2015-12-29 2015-12-29 Information sending method and device Active CN106933848B (en)

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 true CN106933848A (en) 2017-07-07
CN106933848B 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)

Cited By (2)

* Cited by examiner, † Cited by third party
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 A kind of power grid customer service recommended method and device based on intelligent sound 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 (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090144225A1 (en) * 2007-12-03 2009-06-04 Mari Saito Information processing device, information processing terminal, information processing method, and program
CN101882291A (en) * 2010-08-10 2010-11-10 万昌洵 Problem-posing commodity information consultation method based on search engine technique
US20120303376A1 (en) * 2011-05-24 2012-11-29 JVC Kenwood Corporation Information selecting apparatus and method, and computer program
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

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090144225A1 (en) * 2007-12-03 2009-06-04 Mari Saito Information processing device, information processing terminal, information processing method, and program
CN101882291A (en) * 2010-08-10 2010-11-10 万昌洵 Problem-posing commodity information consultation method based on search engine technique
US20120303376A1 (en) * 2011-05-24 2012-11-29 JVC Kenwood Corporation Information selecting apparatus and method, and computer program
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

Cited By (2)

* Cited by examiner, † Cited by third party
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 A kind of power grid customer service recommended method and device based on intelligent sound 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

Also Published As

Publication number Publication date
CN106933848B (en) 2020-10-30

Similar Documents

Publication Publication Date Title
US9449271B2 (en) Classifying resources using a deep network
US9846748B2 (en) Searching for information based on generic attributes of the query
US20180157960A1 (en) Scalable curation system
CN109284363A (en) A kind of answering method, device, electronic equipment and storage medium
CN105808590B (en) Search engine implementation method, searching method and device
KR20180011221A (en) Select representative video frames for videos
CN107633380A (en) The task measures and procedures for the examination and approval and system of a kind of anti-data-leakage system
CN108846126A (en) Generation, question and answer mode polymerization, device and the equipment of related question polymerization model
US20060078862A1 (en) Answer support system, answer support apparatus, and answer support program
EP3113037A1 (en) Adaptive adjustment of network responses to client requests in digital networks
CN102099803A (en) Method and computer system for automatically answering natural language questions
CN108959531A (en) Information search method, device, equipment and storage medium
US8719025B2 (en) Contextual voice query dilation to improve spoken web searching
CN109299245B (en) Method and device for recalling knowledge points
CN110008308B (en) Method and device for supplementing information for user question
CN107590123A (en) Vehicle-mounted middle place context reference resolution method and device
US11789946B2 (en) Answer facts from structured content
CN103593412A (en) Tree-structure-based question answering system and method
US20220308987A1 (en) Debugging applications for delivery via an application delivery server
CN105989066A (en) Information processing method and device
CN106933848A (en) A kind of method for sending information and device
CN105786929B (en) A kind of information monitoring method and device
CN110569435B (en) Intelligent dual-ended recommendation engine system and method
EP3729259B1 (en) Assessing applications for delivery via an application delivery server
Sebastian Deriving Customer Loyalty and Its Determinants from Online Reviews using Support Vector Machine

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