CN106202186A - Service recommendation method based on artificial intelligence and device - Google Patents
Service recommendation method based on artificial intelligence and device Download PDFInfo
- Publication number
- CN106202186A CN106202186A CN201610482073.8A CN201610482073A CN106202186A CN 106202186 A CN106202186 A CN 106202186A CN 201610482073 A CN201610482073 A CN 201610482073A CN 106202186 A CN106202186 A CN 106202186A
- Authority
- CN
- China
- Prior art keywords
- recommendation results
- user
- service
- recommendation
- artificial
- 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
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
- G06F16/951—Indexing; Web crawling techniques
Abstract
The present invention proposes a kind of service recommendation method based on artificial intelligence and device, and wherein, method includes: obtain the service labels corresponding with the searching request of user's input;The network information is carried out big data and processes the candidate result that acquisition is corresponding with service labels;From candidate result, obtain recommendation results according to default screening strategy, recommendation results is fed back to user.The method also feeds back to user for the searching request of user, intelligence, the service recommendation result that quickly acquisition dependency is high, has better met the demand for services of user.
Description
Technical field
The present invention relates to technical field of information processing, particularly relate to a kind of service recommendation method based on artificial intelligence and dress
Put.
Background technology
Artificial intelligence (Artificial Intelligence), english abbreviation is AI.It is research, be developed for simulation,
One new science of technology of theory, method, technology and the application system of the intelligence of extension and extension people.Artificial intelligence is to calculate
One branch of machine science, its attempt understands the essence of intelligence, and produce a kind of new can be in the way of human intelligence be similar
The intelligent machine made a response, the research in this field includes robot, speech recognition, image recognition, natural language processing and specially
Family's system etc..Wherein, the most important aspect of artificial intelligence is exactly speech recognition technology.
Along with the development of Internet technology, online offer is served by waiting also arises at the historic moment.User can be by relevant clothes
Business application send take-away, supermarket, call a taxi, the various searching request such as coffee so that the customer service being served by backstage is fast
Speed is replied according to the searching request of user, meets all kinds of demands for services of user.
But, owing to sending the geographical position of the user of searching request, and the professional variation of searching request, depend on
It is difficult to the good searching request for above-mentioned multiple user by the knowledge structure that customer service self is single reply, and relevant clothes
Business application typically only provides the configurations such as some general, simple clipper service for customer service, and information is single, has no idea as visitor
Clothes provide the recommendation results of intelligence, and therefore, the function services being served by providing is limited.
Summary of the invention
The purpose of the present invention is intended to solve one of above-mentioned technical problem the most to a certain extent.
To this end, the first of the present invention purpose is to propose a kind of service recommendation method based on artificial intelligence.The method
For the searching request of user, intelligence, the service recommendation result that quickly acquisition dependency is high also feed back to user, preferably full
The foot demand for services of user.
Second object of the present invention is to propose a kind of service recommendation device based on artificial intelligence.
To achieve these goals, first aspect present invention embodiment proposes a kind of service recommendation based on artificial intelligence
Method, including:
Obtain the service labels corresponding with the searching request of user's input;
The network information is carried out big data and processes the candidate result that acquisition is corresponding with described service labels;
From described candidate result, obtain recommendation results according to default screening strategy, described recommendation results is fed back to institute
State user.
The service recommendation method based on artificial intelligence of the embodiment of the present invention, obtains corresponding with the searching request of user's input
Service labels after, the network information is carried out big data and processes and obtain the candidate result corresponding with service labels, with according to default
Screening strategy from candidate result, obtain recommendation results, and recommendation results is fed back to user.The method searching for user
Rope is asked, and intelligence, the service recommendation result that quickly acquisition dependency is high also feed back to user, have better met the clothes of user
Business demand.
It addition, the service recommendation method based on artificial intelligence of the embodiment of the present invention, also there is following additional technology special
Levy:
In one embodiment of the invention, the service labels that searching request that described acquisition inputs with user is corresponding, bag
Include:
Analyze described searching request and determine demand key word;
The service labels corresponding with described demand key word is obtained according to default service labels index.
In one embodiment of the invention, described service labels includes at least one of:
Geographical position, user preference feature, price, COS;
Described default screening strategy includes at least one of:
Evaluation, classification, distance, sales volume, credit rating.
In one embodiment of the invention, described recommendation results is fed back to described user, including:
Described recommendation results is sent to many customer service systems confirm;
If described many customer service systems confirm described recommendation results, then described recommendation results is sent to described user;
If described many customer service systems mark artificial recommendation results from described recommendation results, then described artificial recommendation is tied
Fruit is sent to described user.
In one embodiment of the invention, after described artificial recommendation results is sent to described user, also include:
Described recommendation results is updated, in order to the screening strategy that follow-up basis is preset is from described according to described artificial recommendation results
Candidate result obtains described artificial recommendation results.
To achieve these goals, second aspect present invention embodiment proposes a kind of service recommendation based on artificial intelligence
Device, including:
First acquisition module, for obtaining the service labels corresponding with the searching request of user's input;
Second acquisition module, processes, for the network information carries out big data, the candidate that acquisition is corresponding with described service labels
Result;
3rd acquisition module, for obtaining recommendation results according to the screening strategy preset from described candidate result;
Feedback module, for feeding back to described user by described recommendation results.
The service recommendation device based on artificial intelligence of the embodiment of the present invention, obtains corresponding with the searching request of user's input
Service labels after, the network information is carried out big data and processes and obtain the candidate result corresponding with service labels, with according to default
Screening strategy from candidate result, obtain recommendation results, and recommendation results is fed back to user.The method searching for user
Rope is asked, and intelligence, the service recommendation result that quickly acquisition dependency is high also feed back to user, have better met the clothes of user
Business demand.
It addition, the service recommendation device based on artificial intelligence of the embodiment of the present invention also has following additional technology spy
Levy:
In one embodiment of the invention, described first acquisition module is used for:
Analyze described searching request and determine demand key word;
The service labels corresponding with described demand key word is obtained according to default service labels index.
In one embodiment of the invention, described service labels includes at least one of:
Geographical position, user preference feature, price, COS;
Described default screening strategy includes at least one of:
Evaluation, classification, distance, sales volume, credit rating.
In one embodiment of the invention, described feedback module includes:
First transmitting element, confirms for described recommendation results is sent to many customer service systems;
Second transmitting element, for when described many customer service systems confirm described recommendation results, sending out described recommendation results
Give described user;
Described second transmitting element, is additionally operable to mark from described recommendation results in described many customer service systems manually recommend knot
Time really, described artificial recommendation results is sent to described user.
In one embodiment of the invention, described feedback module also includes:
Updating block, for updating described recommendation results according to described artificial recommendation results, in order to follow-up basis is preset
Screening strategy obtains described artificial recommendation results from described candidate result.
Aspect and advantage that the present invention adds will part be given in the following description, and part will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Accompanying drawing explanation
The present invention above-mentioned and/or that add aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially with easy to understand, wherein:
Fig. 1 is the flow chart of based on artificial intelligence according to an embodiment of the invention service recommendation method;
Fig. 2 is the method that recommendation results feeds back to user according to an embodiment of the invention based on many customer service systems
Flow chart;
Fig. 3 is the interface schematic diagram of the most customer service systems;
Fig. 4 is that content corresponding to the identification slot position of the service labels in intelligent search district according to an embodiment of the invention is shown
It is intended to;
Fig. 5 (a)-Fig. 5 (b) is the interface obtaining service recommendation according to an embodiment of the invention based on many customer service systems
Schematic diagram;
Fig. 6 is the structural representation of based on artificial intelligence according to an embodiment of the invention service recommendation device;With
And
Fig. 7 is the structural representation of based on artificial intelligence in accordance with another embodiment of the present invention service recommendation device.
Detailed description of the invention
Embodiments of the invention are described below in detail, and the example of described embodiment is shown in the drawings, the most from start to finish
Same or similar label represents same or similar element or has the element of same or like function.Below with reference to attached
The embodiment that figure describes is exemplary, it is intended to is used for explaining the present invention, and is not considered as limiting the invention.
Below with reference to the accompanying drawings service recommendation method based on artificial intelligence and the device of the embodiment of the present invention are described.
Fig. 1 is the flow chart of based on artificial intelligence according to an embodiment of the invention service recommendation method.
As it is shown in figure 1, the method comprises the steps that
S110, obtains the service labels corresponding with the searching request of user's input.
Generally, traditional is served by, and the searching request for user is replied based on the artificial customer service in backstage,
Such as user sends searching request " specialty in garden restaurant " on being served by, and artificial customer service can knowledge body based on oneself
It is or searches for by means of correlation search engine, providing the user the Search Results of this searching request.
But, owing to sending the difference in the geographical position of the user of searching request, the professional restriction etc. of searching request asks
Topic, artificial customer service knowledge hierarchy based on oneself well cannot provide Search Results for associated user, or artificial customer service needs
To carry out taking turns search by search engine more to obtain Search Results, cause related service application either to provide the effect of Search Results
Rate or professional the highest.
In order to solve the problems referred to above, the service recommendation method based on artificial intelligence of the embodiment of the present invention, by the whole network number
According to excavate and and the mode that processes of the big data such as study, the retrieval to the whole network information and the degree of depth to magnanimity information are excavated and poly-
Close, provide huge search data base for searching request, for the various searching request quick-searchings of user and available from dynamic acquisition
The Search Results of specialty.
Specifically, the service labels that acquisition is corresponding with the searching request of user's input, in one embodiment of the invention,
Can storage demand key word and the corresponding relation of service labels in service labels indexes in advance, thus it is true to analyze searching request
Determine demand key word, obtain the service labels corresponding with demand key word according to default service labels index.Wherein, according to tool
The difference of body application scenarios, service labels can be multiple, such as can include geographical position, user preference feature, price, service
Type etc..
Above-mentioned geographical position can include " near " etc. ambiguity represent the information in geographical position, it is possible to be " in Beijing three
Village " etc. clearly geographical location information etc.;User preference feature can be user for the master of entity corresponding to its searching request
Perception is subject to, and when such as searching request is for food, the preference profiles of user can be " being fond of eating " etc.;Price can be concrete
One price number or an interval, it is also possible to be that ambiguities such as " lowest prices " describes information;COS can include take out,
Purchase by group, film, coffee, cuisines, ticket booking, hotel, prompting, the service of various aspects of the life such as news.
For example, under certain application scenarios, the service labels of the user of acquisition can include restaurant geographical position,
The classification of vegetable, whether purchase by group, whether can band house pet, whether have star to go.
S120, carries out big data and processes the candidate result that acquisition is corresponding with service labels the network information.
It is appreciated that in the network information that big data process, stores service labels and candidate result, this big number in advance
The corresponding relation of service labels and candidate result is had according to storage in the network information processed.
Specifically, after obtaining the service labels corresponding with the searching request being manually entered, inquire about according to this service labels
The network information after the process of above-mentioned big data, obtains corresponding candidate result.Wherein, the kind of the service labels of acquisition is more
Abundant, the candidate result obtained according to service labels will more meet the demands of individuals of user.
S130, obtains recommendation results from candidate result according to default screening strategy, recommendation results is fed back to user.
Specifically, in order to filter out the Search Results more conforming to user search request further, can be according to default
Screening strategy obtains the recommendation results that most probable meets the searching request of user from candidate result, and recommendation results is fed back to use
Family.
Wherein, according to the difference of concrete application scenarios, the screening mode of default screening strategy is the most different, this screening strategy
Evaluation, classification, distance, sales volume, credit rating etc. can be included.
For example, after obtaining the multiple candidate result corresponding with service labels, can be by candidate result according to candidate
Result sorts to remote near with the distance of the user sending searching request, thus can be by multiple candidate result close together
Screen, feed back to user as recommendation results.
In sum, the service recommendation method based on artificial intelligence of the embodiment of the present invention, obtain and searching that user inputs
After the service labels that rope request is corresponding, the network information is carried out big data and processes the candidate result that acquisition is corresponding with service labels,
To obtain recommendation results from candidate result according to the screening strategy preset, and recommendation results is fed back to user.The method pin
Searching request to user, intelligence, the service recommendation result that quickly acquisition dependency is high also feed back to user, better meet
The demand for services of user.
Based on above example, in actual applications, the recommendation obtained from candidate result according to default screening strategy
After result, in order to recommend more excellent recommendation results to user further, also can introduce many customer service systems and recommendation results is entered
The selection etc. of one step.
The service recommendation method based on artificial intelligence of above-described embodiment can be applied in many customer service systems, many customer services
System, according to the searching request of user, uses the service recommendation method based on artificial intelligence of above-described embodiment to obtain and recommends knot
Really, and the various information of the above-mentioned recommendation results of comprehensive consideration, such as evaluation, credit etc., in recommendation results, artificial selection is optimum
Recommendation results etc., and then artificial recommendation results is fed back to user.
2-Fig. 5 is combined in the implementation process of artificial selection's recommendation results in recommendation results below in conjunction with the accompanying drawings, describes in detail
The service recommendation method based on artificial intelligence of the embodiment of the present invention, is described as follows:
Fig. 2 is the method that recommendation results feeds back to user according to an embodiment of the invention based on many customer service systems
Flow chart, as in figure 2 it is shown, the method includes:
S210, analyzes searching request and determines demand key word.
S220, obtains the service labels corresponding with demand key word according to default service labels index.
Specifically, can in advance service labels index in storage demand key word and the corresponding relation of service labels, thus
Searching request can be analyzed and determine demand key word, obtain the service corresponding with demand key word according to default service labels index
Label.
S230, carries out big data and processes the candidate result that acquisition is corresponding with service labels the network information.
S240, obtains recommendation results according to default screening strategy from candidate result, recommendation results is sent to the most objective
Dress system confirms.
S250, if many customer service systems confirm recommendation results, is then sent to user by recommendation results.
Specifically, if according to default screening strategy, the recommendation results obtained from candidate result is integrated ordered more excellent,
The restaurant that the recommendation results that such as obtains from candidate result according to screening strategy is corresponding, the nearer several restaurants of distance users are commented
Valency and credit etc. are also preferable, and the most customer service systems confirm this recommendation results, so that recommendation results is sent to user.
S260, if many customer service systems mark artificial recommendation results from recommendation results, then sends artificial recommendation results
To user.
Specifically, if according to default screening strategy, in the recommendation results obtained from candidate result, come above
Recommendation results is not integrated ordered high, therefore, integrated ordered higher recommendation results can be labeled as in recommendation results
Artificial recommendation results, thus artificial recommendation results is sent to user.
Such as, the searching request obtaining user's input is " neighbouring nice take-away ", acquisition corresponding with this searching request
Service labels be geographical position and user preference feature, the network information is being carried out big data process obtain with above-mentioned service mark
After signing corresponding candidate result, recommendation results can be carried out integrated ordered according to comprehensive, sales volume, price etc. by many customer service systems, enters
And integrated ordered higher recommendation results can be labeled as artificial recommendation results, and this artificial recommendation results is sent to user.
The most such as, obtain user input searching request be " recommending the dining room of about 100 yuan to me ", acquisition with
Service labels corresponding to this searching request is geographical position and price etc., the network information is carried out big data process obtain with on
After stating the candidate result that service labels is corresponding, recommendation results being sent to many customer service systems, the customer service of many customer service systems can will push away
Recommend and result meets three dining rooms of user's request be labeled as artificial recommendation results, and be sent to this artificial recommendation results use
Family.
The most such as, obtain user input searching request be " having what good film recently ", acquisition with this searching request
Corresponding service labels is geographical position and film etc., processes acquisition and above-mentioned service labels the network information carries out big data
After corresponding candidate result, recommendation results is sent to many customer service systems, the customer service of many customer service systems can by recommendation results according to
Evaluate and classification is ranked up, and then be labeled as artificial recommendation results by evaluating the Search Results with classification front three, and should
Artificial recommendation results is sent to user.
It is appreciated that in an embodiment of the present invention, when the service labels obtained is similar to, the network information is counted greatly
After the candidate result corresponding with service labels according to processing acquisition, the recommendation obtained from candidate result according to default screening strategy
Result is relatively-stationary, and therefore, it is the most more consistent that many customer service systems mark artificial recommendation results from recommendation results, thus i.e.
Making customer service different, the artificial recommendation results being sent to user is the most relatively uniform, preferably ensure that many customer service systems are that user carries
The uniformity of the Search Results of confession.
S270, updates recommendation results according to artificial recommendation results, in order to the screening strategy that follow-up basis is preset is tied from candidate
Artificial recommendation results is obtained in Guo.
Specifically, recommendation results can be continued to optimize according to the artificial recommendation results of user, in order to follow-up basis is preset
Screening strategy obtains artificial recommendation results from candidate result, it is achieved human assistance systematic learning is to improve constantly what system obtained
The accuracy of Search Results.
In order to more clearly describe in the service recommendation method based on artificial intelligence of the embodiment of the present invention, how to combine
Many customer service systems, recommend more excellent recommendation results to user, below in conjunction with concrete application scenarios, the base to the embodiment of the present invention
Service recommendation method in artificial intelligence is illustrated.
In this example, application scenarios is user in many customer service systems for the relevant search of cuisines, from candidate result
The screening strategy obtaining recommendation results is according to distance screening, is illustrated below:
As it is shown on figure 3, these many customer service systems can be divided into left and right, in three row, the left side one is classified as visitor's access list district,
Middle one is classified as present chatting window district, and the right one is classified as the intelligent search district that the searching request for user scans for.
As shown in Figure 4, the identification slot position of the service labels in intelligent search district includes COS, geographical position, price, people
Number, style of cooking classification, dining room name, whether purchase by group, whether have star to patronize.
Intelligent search district can include search box region, hurdle, address of service and service search supplementary module etc..Wherein,
Search box for inputting the searching request of user, hurdle, address of service acquiescence be given currently can the positioning address at family, customer service can be
Other addresses of this address field manual editing are as service search address, and service search supplementary module includes taking out, purchases by group, film etc.
Vertical class service.
Specifically, at the search box in the many customer service systems intelligent search district as shown in Fig. 5 (a), the searching request of input is
Time " dining room of having a dinner party being suitable for 10 people of neighbouring about 100 yuan is recommended ", obtain the service corresponding with the searching request of user's input
Label, wherein, the most as shown in Figure 4, include the identification of service labels price identifying price be less than 20 yuan, 20-50 first,
The identification of which price range such as 50-80 unit, 80-120 unit, and the identification number etc. to people.
And then, as shown in Fig. 5 (a), the label that the searching request of user's input of acquisition is corresponding is: the position of the user of location
Putting is building, Technology Park the 1st, and price is 100-150 unit etc..
After the network information is carried out the candidate result that the process acquisition of big data is corresponding with above-mentioned service labels, recommendation is tied
Fruit display is on the interface in intelligent search region, and the customer service of many customer service systems can meet three of user's request in recommendation results
Dining room is labeled as artificial recommendation results, and this artificial recommendation results is sent to user.As shown in Fig. 5 (b), customer service is according to candidate
Result selects three dining rooms to be Wushan grilled fish, Shu Zhengyuan chaffy dish, room, childlike innocence kitchen, and then can be at current chat window as shown in Figure 3
The link in these three dining rooms is sent to user by port area.
In sum, the service recommendation method based on artificial intelligence of the embodiment of the present invention, the most anti-by recommendation results
Feed before user, recommendation results is sent to many customer service systems and confirms, recommend knot for many customer service systems comprehensive consideration
The various information of fruit, such as evaluation, credit etc., the recommendation results that artificial selection is optimum in recommendation results, and then will manually push away
Recommend result and feed back to user.Further ensure recommendation results and better meet the demand of user.
In order to realize above-described embodiment, the invention allows for a kind of service recommendation device based on artificial intelligence.Fig. 6 is
The structural representation of based on artificial intelligence according to an embodiment of the invention service recommendation device, as shown in Figure 6, this device
Including: the first acquisition module the 100, second acquisition module the 200, the 3rd acquisition module 300 and feedback module 400.
Wherein, the first acquisition module 100, for obtaining the service labels corresponding with the searching request of user's input.
Specifically, the first acquisition module 100 obtains the service labels corresponding with the searching request of user's input, in the present invention
An embodiment in, the first acquisition module 100 can in advance service labels index in storage demand key word and service labels
Corresponding relation, thus searching request can be analyzed and determine demand key word, obtain and demand according to default service labels index
The service labels that key word is corresponding.Wherein, according to the difference of concrete application scenarios, service labels can be multiple, such as can wrap
Include geographical position, user preference feature, price, COS etc..
Above-mentioned geographical position can include " near " etc. ambiguity represent the information in geographical position, it is possible to be " in Beijing three
Village " etc. clearly geographical location information etc.;User preference feature can be user for the master of entity corresponding to its searching request
Perception is subject to, and when such as searching request is for food, the preference profiles of user can be " being fond of eating " etc.;Price can be concrete
One price number or an interval, it is also possible to be that ambiguities such as " lowest prices " describes information;COS can include take out,
Purchase by group, film, coffee, cuisines, ticket booking, hotel, prompting, the service of various aspects of the life such as news.
Second acquisition module 200, processes, for the network information carries out big data, the candidate that acquisition is corresponding with service labels
Result.
It is appreciated that in the network information that big data process, stores service labels and candidate result, this big number in advance
The corresponding relation of service labels and candidate result is had according to storage in the network information processed.
Specifically, after the first acquisition module 100 obtains the service labels corresponding with the searching request being manually entered, second
Acquisition module 200 inquires about the network information after above-mentioned big data process according to this service labels, obtains corresponding candidate's knot
Really.Wherein, the kind of the service labels of acquisition is the abundantest, will more meet user's according to the candidate result that service labels obtains
Demands of individuals.
3rd acquisition module 300, for obtaining recommendation results according to the screening strategy preset from candidate result.
Feedback module 400, for feeding back to user by recommendation results.
Specifically, in order to filter out the Search Results more conforming to user search request further, the 3rd acquisition module 300
The recommendation results that most probable meets the searching request of user can be obtained from candidate result according to default screening strategy, and then
Recommendation results is fed back to user by feedback module 400.
Wherein, according to the difference of concrete application scenarios, the screening mode of default screening strategy is the most different, this screening strategy
Evaluation, classification, distance, sales volume, credit rating etc. can be included.
In sum, the service recommendation device based on artificial intelligence of the embodiment of the present invention, obtain and searching that user inputs
After the service labels that rope request is corresponding, the network information is carried out big data and processes the candidate result that acquisition is corresponding with service labels,
To obtain recommendation results from candidate result according to the screening strategy preset, and recommendation results is fed back to user.This device pin
Searching request to user, intelligence, the service recommendation result that quickly acquisition dependency is high also feed back to user, better meet
The demand for services of user.
Based on above example, in actual applications, the recommendation obtained from candidate result according to default screening strategy
After result, in order to recommend more excellent recommendation results to user further, also can introduce many customer service systems and recommendation results is entered
The selection etc. of one step.
The service recommendation device based on artificial intelligence of above-described embodiment can be applied in many customer service systems, many customer services
System, according to the searching request of user, uses the service recommendation method based on artificial intelligence of above-described embodiment to obtain and recommends knot
Really, and the various information of the above-mentioned recommendation results of comprehensive consideration, such as evaluation, credit etc., in recommendation results, artificial selection is optimum
Recommendation results etc., and then artificial recommendation results is fed back to user.
7 it is combined in the implementation process of artificial selection's recommendation results in recommendation results below in conjunction with the accompanying drawings, describes this in detail
The service recommendation device based on artificial intelligence of bright embodiment, is described as follows:
Fig. 7 is the structural representation of based on artificial intelligence in accordance with another embodiment of the present invention service recommendation device,
As it is shown in fig. 7, on the basis of shown in Fig. 6, this feedback module 400 includes: first transmitting element the 410, second transmitting element 420
With updating block 430.
Wherein, the first transmitting element 410 for the 3rd acquisition module 300 according to default screening strategy from candidate result
After obtaining recommendation results, recommendation results is sent to many customer service systems and confirms.
Second transmitting element 420, for when many customer service systems confirm recommendation results, being sent to user by recommendation results.
Specifically, if according to default screening strategy, the recommendation results obtained from candidate result is integrated ordered more excellent,
The restaurant that the recommendation results that such as obtains from candidate result according to screening strategy is corresponding, the nearer several restaurants of distance users are commented
Valency and credit etc. are also preferable, and the most customer service systems confirm this recommendation results, and the second transmitting element 420 is to send recommendation results
To user.
If more specifically, according to default screening strategy, in the recommendation results obtained from candidate result, come before
Recommendation results be not integrated ordered high, therefore, can be by integrated ordered higher recommendation results mark in recommendation results
For artificial recommendation results, thus artificial recommendation results is sent to user by the second transmitting element 420.
Updating block 430 is for updating recommendation results according to artificial recommendation results, in order to the screening plan that follow-up basis is preset
From candidate result, slightly obtain artificial recommendation results.
Specifically, updating block 430 can continue to optimize recommendation results according to the artificial recommendation results of user, in order to follow-up
From candidate result, artificial recommendation results is obtained, it is achieved human assistance systematic learning is to improve constantly according to default screening strategy
The accuracy of the Search Results that system obtains.
It should be noted that the service recommendation device based on artificial intelligence of the embodiment of the present invention, with above-mentioned with reference to Fig. 1-
The service recommendation method based on artificial intelligence that Fig. 5 describes is corresponding, the service recommendation based on artificial intelligence of the embodiment of the present invention
The details that device does not discloses, does not repeats them here.
In sum, the service recommendation device based on artificial intelligence of the embodiment of the present invention, the most anti-by recommendation results
Feed before user, recommendation results is sent to many customer service systems and confirms, recommend knot for many customer service systems comprehensive consideration
The various information of fruit, such as evaluation, credit etc., the recommendation results that artificial selection is optimum in recommendation results, and then will manually push away
Recommend result and feed back to user.Further ensure recommendation results and better meet the demand of user.
In the description of this specification, reference term " embodiment ", " some embodiments ", " example ", " specifically show
Example " or the description of " some examples " etc. means to combine this embodiment or example describes specific features, structure, material or spy
Point is contained at least one embodiment or the example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be in office
One or more embodiments or example combine in an appropriate manner.Additionally, in the case of the most conflicting, the skill of this area
The feature of the different embodiments described in this specification or example and different embodiment or example can be tied by art personnel
Close and combination.
Although above it has been shown and described that embodiments of the invention, it is to be understood that above-described embodiment is example
Property, it is impossible to being interpreted as limitation of the present invention, those of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, revises, replaces and modification.
Claims (10)
1. a service recommendation method based on artificial intelligence, it is characterised in that comprise the following steps:
Obtain the service labels corresponding with the searching request of user's input;
The network information is carried out big data and processes the candidate result that acquisition is corresponding with described service labels;
From described candidate result, obtain recommendation results according to default screening strategy, described recommendation results is fed back to described use
Family.
2. the method for claim 1, it is characterised in that the service that searching request that described acquisition inputs with user is corresponding
Label, including:
Analyze described searching request and determine demand key word;
The service labels corresponding with described demand key word is obtained according to default service labels index.
3. method as claimed in claim 2, it is characterised in that
Described service labels includes at least one of:
Geographical position, user preference feature, price, COS;
Described default screening strategy includes at least one of:
Evaluation, classification, distance, sales volume, credit rating.
4. the method for claim 1, it is characterised in that described recommendation results is fed back to described user, including:
Described recommendation results is sent to many customer service systems confirm;
If described many customer service systems confirm described recommendation results, then described recommendation results is sent to described user;
If described many customer service systems mark artificial recommendation results from described recommendation results, then described artificial recommendation results is sent out
Give described user.
5. method as claimed in claim 4, it is characterised in that after described artificial recommendation results is sent to described user,
Also include:
Described recommendation results is updated, in order to the screening strategy that follow-up basis is preset is from described candidate according to described artificial recommendation results
Result obtains described artificial recommendation results.
6. a service recommendation device based on artificial intelligence, it is characterised in that include
First acquisition module, for obtaining the service labels corresponding with the searching request of user's input;
Second acquisition module, processes, for the network information carries out big data, candidate's knot that acquisition is corresponding with described service labels
Really;
3rd acquisition module, for obtaining recommendation results according to the screening strategy preset from described candidate result;
Feedback module, for feeding back to described user by described recommendation results.
7. device as claimed in claim 6, it is characterised in that described first acquisition module is used for:
Analyze described searching request and determine demand key word;
The service labels corresponding with described demand key word is obtained according to default service labels index.
8. device as claimed in claim 7, it is characterised in that
Described service labels includes at least one of:
Geographical position, user preference feature, price, COS;
Described default screening strategy includes at least one of:
Evaluation, classification, distance, sales volume, credit rating.
9. device as claimed in claim 6, it is characterised in that described feedback module includes:
First transmitting element, confirms for described recommendation results is sent to many customer service systems;
Second transmitting element, for when described many customer service systems confirm described recommendation results, being sent to described recommendation results
Described user;
Described second transmitting element, is additionally operable to mark artificial recommendation results from described recommendation results in described many customer service systems
Time, described artificial recommendation results is sent to described user.
10. device as claimed in claim 9, it is characterised in that described feedback module also includes:
Updating block, for updating described recommendation results according to described artificial recommendation results, in order to the screening that follow-up basis is preset
Strategy obtains described artificial recommendation results from described candidate result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610482073.8A CN106202186B (en) | 2016-06-27 | 2016-06-27 | Service recommendation method and device based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610482073.8A CN106202186B (en) | 2016-06-27 | 2016-06-27 | Service recommendation method and device based on artificial intelligence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106202186A true CN106202186A (en) | 2016-12-07 |
CN106202186B CN106202186B (en) | 2020-10-30 |
Family
ID=57462209
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610482073.8A Active CN106202186B (en) | 2016-06-27 | 2016-06-27 | Service recommendation method and device based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106202186B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107291930A (en) * | 2017-06-29 | 2017-10-24 | 环球智达科技(北京)有限公司 | The computational methods of weight number |
CN107451274A (en) * | 2017-08-04 | 2017-12-08 | 百度在线网络技术(北京)有限公司 | Aid in method for pushing, device, equipment and the storage medium of customer service information |
CN107679246A (en) * | 2017-10-31 | 2018-02-09 | 努比亚技术有限公司 | A kind of present method for pushing, terminal and computer-readable recording medium based on social networking application |
CN107909439A (en) * | 2017-11-16 | 2018-04-13 | 阿里巴巴集团控股有限公司 | The recommendation method, apparatus and electronic equipment of shared product |
CN109815259A (en) * | 2018-11-08 | 2019-05-28 | 平安科技(深圳)有限公司 | The configuration method of service field, device, computer equipment and computer storage medium in gateway |
CN109903115A (en) * | 2017-12-08 | 2019-06-18 | 财团法人工业技术研究院 | Electronic device, the rendering method of decision process module and computer-readable media |
CN110322093A (en) * | 2018-03-30 | 2019-10-11 | 阿里巴巴集团控股有限公司 | Information processing method, information display method, device and calculating equipment |
WO2020010954A1 (en) * | 2018-07-09 | 2020-01-16 | 阿里巴巴集团控股有限公司 | Offline immediate demand processing method, information recommendation method and apparatus, and device |
CN110851703A (en) * | 2019-09-30 | 2020-02-28 | 口碑(上海)信息技术有限公司 | Data processing method and device |
CN110941631A (en) * | 2019-10-30 | 2020-03-31 | 联想(北京)有限公司 | Information processing method and electronic equipment |
WO2020143351A1 (en) * | 2019-01-08 | 2020-07-16 | 北京三快在线科技有限公司 | Area comprehensive recommendation method, electronic device, and readable storage medium |
CN111581245A (en) * | 2020-03-26 | 2020-08-25 | 口口相传(北京)网络技术有限公司 | Data searching method and device |
CN112417310A (en) * | 2019-08-21 | 2021-02-26 | 上海掌门科技有限公司 | Method for establishing intelligent service index and recommending intelligent service |
CN112905878A (en) * | 2021-01-25 | 2021-06-04 | 长沙市到家悠享网络科技有限公司 | Corresponding relation configuration method, device, equipment and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140244612A1 (en) * | 2013-02-28 | 2014-08-28 | Linkedln Corporation | Techniques for quantifying the intent and interests of members of a social networking service |
CN104035957A (en) * | 2014-04-14 | 2014-09-10 | 百度在线网络技术(北京)有限公司 | Search method and device |
CN104239457A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术(北京)有限公司 | Search recommending method and device |
CN104281699A (en) * | 2014-10-15 | 2015-01-14 | 百度在线网络技术(北京)有限公司 | Search recommending method and device |
US20150127631A1 (en) * | 2013-11-05 | 2015-05-07 | International Business Machines Corporation | Best available alternative dialog |
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
CN105426436A (en) * | 2015-11-05 | 2016-03-23 | 百度在线网络技术(北京)有限公司 | Artificial intelligent robot based information provision method and apparatus |
CN105591882A (en) * | 2015-12-10 | 2016-05-18 | 北京中科汇联科技股份有限公司 | Method and system for mixed customer services of intelligent robots and human beings |
-
2016
- 2016-06-27 CN CN201610482073.8A patent/CN106202186B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140244612A1 (en) * | 2013-02-28 | 2014-08-28 | Linkedln Corporation | Techniques for quantifying the intent and interests of members of a social networking service |
US20150127631A1 (en) * | 2013-11-05 | 2015-05-07 | International Business Machines Corporation | Best available alternative dialog |
CN104035957A (en) * | 2014-04-14 | 2014-09-10 | 百度在线网络技术(北京)有限公司 | Search method and device |
CN104239457A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术(北京)有限公司 | Search recommending method and device |
CN104281699A (en) * | 2014-10-15 | 2015-01-14 | 百度在线网络技术(北京)有限公司 | Search recommending method and device |
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
CN105426436A (en) * | 2015-11-05 | 2016-03-23 | 百度在线网络技术(北京)有限公司 | Artificial intelligent robot based information provision method and apparatus |
CN105591882A (en) * | 2015-12-10 | 2016-05-18 | 北京中科汇联科技股份有限公司 | Method and system for mixed customer services of intelligent robots and human beings |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107291930A (en) * | 2017-06-29 | 2017-10-24 | 环球智达科技(北京)有限公司 | The computational methods of weight number |
CN107451274A (en) * | 2017-08-04 | 2017-12-08 | 百度在线网络技术(北京)有限公司 | Aid in method for pushing, device, equipment and the storage medium of customer service information |
CN107451274B (en) * | 2017-08-04 | 2020-11-27 | 上海优扬新媒信息技术有限公司 | Method, device and equipment for pushing auxiliary customer service information and storage medium |
CN107679246A (en) * | 2017-10-31 | 2018-02-09 | 努比亚技术有限公司 | A kind of present method for pushing, terminal and computer-readable recording medium based on social networking application |
TWI701629B (en) * | 2017-11-16 | 2020-08-11 | 香港商阿里巴巴集團服務有限公司 | Recommended method, device and electronic equipment for sharing products |
CN107909439A (en) * | 2017-11-16 | 2018-04-13 | 阿里巴巴集团控股有限公司 | The recommendation method, apparatus and electronic equipment of shared product |
WO2019095846A1 (en) * | 2017-11-16 | 2019-05-23 | 阿里巴巴集团控股有限公司 | Shared product recommendation method and apparatus, and electronic device |
US10956976B2 (en) | 2017-11-16 | 2021-03-23 | Advanced New Technologies Co., Ltd. | Recommending shared products |
CN109903115A (en) * | 2017-12-08 | 2019-06-18 | 财团法人工业技术研究院 | Electronic device, the rendering method of decision process module and computer-readable media |
US11087218B2 (en) | 2017-12-08 | 2021-08-10 | Industrial Technology Research Institute | Electronic device, presentation method for decision-making process module and computer readable medium |
CN110322093A (en) * | 2018-03-30 | 2019-10-11 | 阿里巴巴集团控股有限公司 | Information processing method, information display method, device and calculating equipment |
CN110322093B (en) * | 2018-03-30 | 2024-03-08 | 阿里巴巴集团控股有限公司 | Information processing method, information display method, information processing device and computing equipment |
WO2020010954A1 (en) * | 2018-07-09 | 2020-01-16 | 阿里巴巴集团控股有限公司 | Offline immediate demand processing method, information recommendation method and apparatus, and device |
CN109815259A (en) * | 2018-11-08 | 2019-05-28 | 平安科技(深圳)有限公司 | The configuration method of service field, device, computer equipment and computer storage medium in gateway |
CN109815259B (en) * | 2018-11-08 | 2023-06-06 | 平安科技(深圳)有限公司 | Configuration method, device, equipment and storage medium of service field in gateway |
WO2020143351A1 (en) * | 2019-01-08 | 2020-07-16 | 北京三快在线科技有限公司 | Area comprehensive recommendation method, electronic device, and readable storage medium |
CN112417310B (en) * | 2019-08-21 | 2023-10-03 | 上海掌门科技有限公司 | Method for establishing intelligent service index and recommending intelligent service |
CN112417310A (en) * | 2019-08-21 | 2021-02-26 | 上海掌门科技有限公司 | Method for establishing intelligent service index and recommending intelligent service |
CN110851703A (en) * | 2019-09-30 | 2020-02-28 | 口碑(上海)信息技术有限公司 | Data processing method and device |
CN110941631A (en) * | 2019-10-30 | 2020-03-31 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN110941631B (en) * | 2019-10-30 | 2024-01-23 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN111581245A (en) * | 2020-03-26 | 2020-08-25 | 口口相传(北京)网络技术有限公司 | Data searching method and device |
CN111581245B (en) * | 2020-03-26 | 2023-10-17 | 口口相传(北京)网络技术有限公司 | Data searching method and device |
CN112905878B (en) * | 2021-01-25 | 2023-03-10 | 长沙市到家悠享网络科技有限公司 | Corresponding relation configuration method, device, equipment and storage medium |
CN112905878A (en) * | 2021-01-25 | 2021-06-04 | 长沙市到家悠享网络科技有限公司 | Corresponding relation configuration method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN106202186B (en) | 2020-10-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106202186A (en) | Service recommendation method based on artificial intelligence and device | |
CN105426436B (en) | Information providing method and device based on artificial intelligence robot | |
US11481461B2 (en) | Concept networks and systems and methods for the creation, update and use of same to select images, including the selection of images corresponding to destinations in artificial intelligence systems | |
US11501763B2 (en) | Machine learning tool for navigating a dialogue flow | |
KR102301899B1 (en) | Information Retrieval Methods, Devices and Systems | |
US10115118B2 (en) | Obtaining event reviews | |
CN103559636B (en) | Restaurant management system based on cloud computing and intelligent analysis | |
US11768893B2 (en) | Concept networks and systems and methods for the creation, update and use of same in artificial intelligence systems | |
US8572116B2 (en) | System for recommending an article not present in an image | |
CN102929483B (en) | Terminal and resource sharing method | |
US20160364815A1 (en) | Multi-Passenger Travel Booking Platform | |
CN106951516B (en) | Decoration selection intelligent sorting method based on big data | |
US11138249B1 (en) | Systems and methods for the creation, update and use of concept networks to select destinations in artificial intelligence systems | |
CN112672188B (en) | Method, equipment and storage medium for recommending anchor | |
KR102645521B1 (en) | system that provides advertising information for restaurants | |
CN108256970A (en) | A kind of method that Products Show is carried out based on shopping need | |
CN108711082A (en) | Recommend method, apparatus, Server for catering and storage medium in dining room | |
CN103678624A (en) | Searching method, searching server, and searching request executing method and terminal | |
US20210133641A1 (en) | Multi-passenger and multiattribute travel booking platform | |
KR20150145383A (en) | Providing Social Network Service And Providing Contents For The Same | |
JP2019531516A (en) | Interest search guide system by field of interest | |
CN111752982A (en) | Information processing method and device | |
US11514495B2 (en) | Creating custom objects from a static list of objects and turning the custom objects into trends | |
CN105378626A (en) | Situation-aware presentation of information | |
TW201812649A (en) | Instant reservation platform providing online reservation services without installing a large number of business applications in a mobile device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |