CN109492103A - Label information acquisition methods, device, electronic equipment and computer-readable medium - Google Patents
Label information acquisition methods, device, electronic equipment and computer-readable medium Download PDFInfo
- Publication number
- CN109492103A CN109492103A CN201811333350.4A CN201811333350A CN109492103A CN 109492103 A CN109492103 A CN 109492103A CN 201811333350 A CN201811333350 A CN 201811333350A CN 109492103 A CN109492103 A CN 109492103A
- Authority
- CN
- China
- Prior art keywords
- agreement
- address
- honouring
- user
- classification results
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000006399 behavior Effects 0.000 claims description 39
- 238000004458 analytical method Methods 0.000 claims description 24
- 239000013598 vector Substances 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 16
- 238000013145 classification model Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 7
- 238000011430 maximum method Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 230000006854 communication Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000005291 magnetic effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a kind of label information acquisition methods, device, electronic equipment and computer-readable medium, belongs to Internet technical field.The label information acquisition methods include: to classify to the address of honouring an agreement of user, the classification results for the address that obtains honouring an agreement, wherein the address of honouring an agreement is the address that the user honours an agreement to order；It is analyzed for the behavior of honouring an agreement of the address of honouring an agreement in conjunction with the classification results according to the user, obtains the label information of the user.This method is classified by the address of honouring an agreement to user, it is analyzed to obtain the label information of user in conjunction with the behavior of honouring an agreement of user, such as the relatively stronger Financial Attribute such as occupation, house property value, living habit, the consuming capacity of user is assessed under the premise of not needing to obtain the sensitive information of user.
Description
Technical field
The present disclosure generally relates to Internet technical field, in particular to a kind of label information acquisition methods, device,
Electronic equipment and computer-readable medium.
Background technique
In traditional financial industry, proved generally by bank's flowing water, common reserve fund social security, Individual Income Tax, the Certificate of House Property, on-job card
Bright combination client declares fill message to obtain the information such as the income level of user, consuming capacity, loan repayment capacity.But for
Internet financial platform, we directly acquire occupation there is no method and house property is worth relevant information.
Therefore, there is also the places that has much room for improvement in technical solution in the prior art.
Above- mentioned information are only used for reinforcing the understanding to the background of the disclosure, therefore it disclosed in the background technology part
It may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure provides a kind of label information acquisition methods, device, electronic equipment and computer-readable medium, solves above-mentioned
At least one problem in problem.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the one side of the disclosure, a kind of label information acquisition methods are provided, comprising:
Classify to the address of honouring an agreement of user, the classification results for the address that obtains honouring an agreement, wherein described honour an agreement address as institute
State the address that user honours an agreement to order；The behavior of honouring an agreement of the address of honouring an agreement is directed in conjunction with the classification according to the user
As a result it is analyzed, obtains the label information of the user.
In one embodiment of the present disclosure, the behavior of honouring an agreement of the address of honouring an agreement is directed in conjunction with described according to the user
Classification results are analyzed, and the label information for obtaining the user includes:
Attributive analysis is carried out to the classification results in conjunction with trade information database, obtains the attribute letter of the address of honouring an agreement
Breath；
The behavior of honouring an agreement of the address of honouring an agreement is directed in conjunction with the classification results and the attribute information according to the user
It is analyzed, obtains the label information of the user.
In one embodiment of the present disclosure, the classification that is described to classify to the address of honouring an agreement, obtaining honouring an agreement address
Result includes:
Classification annotation is carried out to history address of honouring an agreement based on term vector, the mapping relations of obtain honouring an agreement address and classification,
Described in history address of honouring an agreement be the address honoured an agreement to History Order of multiple users in platform；
The classification results are obtained in conjunction with the mapping relations of honour an agreement address and the classification for the address of honouring an agreement.
In one embodiment of the present disclosure, based on term vector to history honour an agreement address carry out classification annotation include:
It honours an agreement from the history and extracts trunk information in address；The trunk information is segmented by participle technique,
Obtain multiple address participles；The multiple address participle is converted to term vector；The term vector is clustered；According to cluster
As a result corresponding classification annotation is carried out to the classification results of the trunk information of the address of honouring an agreement.
In one embodiment of the present disclosure, the classification that is described to classify to the address of honouring an agreement, obtaining honouring an agreement address
Result includes:
Word-based feature to history honour an agreement address carry out Softmax training, textual classification model is obtained, wherein the history
Address of honouring an agreement is the address honoured an agreement to History Order of multiple users in platform；
The address of honouring an agreement is input to the textual classification model, exports the classification results.
In one embodiment of the present disclosure, word-based feature to history honour an agreement address carry out Softmax training include:
The rule of correspondence of configuration address text and classification；History address of honouring an agreement is matched using multimode matching,
Address and the address text matches if the history is honoured an agreement export corresponding classification results according to the rule of correspondence；
The address of honouring an agreement is segmented, and multiplexed combination is carried out to obtained participle, the spy based on single participle or multiple participles
Sign carries out Softmax training, obtains the textual classification model.
In one embodiment of the present disclosure, in conjunction with trade information database to the classification results carry out attributive analysis it
Before, further includes:
Trade classification information is pre-processed；According to pretreated trade classification information architecture trade information data
Library；
Wherein include a plurality of information in the trade information database, includes: in information described in each
Label；Classification results；Attribute information；
The classification results include: at least one of house, hospital, hotel, office building, Recreational places or more
It is a；The attribute information include: room rate, hospital category, Hotel Star, office building grade, in Recreational places grade extremely
Few one or more.
In one embodiment of the present disclosure, attributive analysis is carried out to the classification results in conjunction with trade information database,
Obtain attribute information:
By carrying out Forward Maximum Method to the information in the classification results and the trade information database, institute is obtained
State the corresponding attribute information in address of honouring an agreement.
In one embodiment of the present disclosure, the behavior of honouring an agreement of the address of honouring an agreement is directed in conjunction with the classification according to user
As a result before being analyzed, further includes:
The user is obtained for the behavior of honouring an agreement of the address of honouring an agreement；Wherein the behavior of honouring an agreement includes: and carries out on working day
About number, nonworkdays honour an agreement number, date span of honouring an agreement and the user at least one in the markup information for address of honouring an agreement
Kind.
In one embodiment of the present disclosure, the behavior of honouring an agreement of the address of honouring an agreement is directed in conjunction with described according to the user
Classification results are analyzed, and the label information for obtaining the user includes:
If the working day of the user honours an agreement, number is more than or equal to first threshold, and the classification results are hospital, then
It is medical worker that the label information for obtaining the user, which is occupation,.
In one embodiment of the present disclosure, the behavior of honouring an agreement of the address of honouring an agreement is directed in conjunction with described according to the user
Classification results and the attribute information are analyzed, and the label information for obtaining the user includes:
If the nonworkdays of the user is honoured an agreement, number is more than or equal to second threshold, and the classification results are house,
And the room rate in the attribute information is more than or equal to third threshold value, then the label information for obtaining the user is high-end cell.
According to the another further aspect of the disclosure, a kind of label information acquisition device is provided, comprising: address sort module, configuration
Classify for the address of honouring an agreement to user, the classification results for the address that obtains honouring an agreement, wherein the address of honouring an agreement is the user
The address honoured an agreement to order；Label analysis module is configured to the row of honouring an agreement according to the user for the address of honouring an agreement
To be analyzed in conjunction with the classification results, the label information of the user is obtained.
According to the another aspect of the disclosure, a kind of electronic equipment, including processor are provided；Memory, storage is for described
Processor controls the instruction of method and step as described above.
According to another aspect of the present disclosure, a kind of computer-readable medium is provided, the executable finger of computer is stored thereon with
It enables, the executable instruction realizes method and step as described above when being executed by processor.
According to the embodiment of the present disclosure provide label information acquisition methods, device, electronic equipment and computer-readable medium,
Classification 7268 is carried out by the address of honouring an agreement to user, is analyzed to obtain the label letter of user in conjunction with the behavior of honouring an agreement of user
Breath, such as the relatively stronger Financial Attribute such as occupation, house property value, living habit, in the sensitive information for not needing acquisition user
Under the premise of assess user consuming capacity.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other target, feature and the advantage of the disclosure will
It becomes more fully apparent.
Fig. 1 shows a kind of flow chart of the label information acquisition methods provided in one embodiment of the disclosure.
Fig. 2 shows the flow charts of another label information acquisition methods provided in one embodiment of the disclosure.
Fig. 3 shows the flow chart for carrying out classification annotation in one embodiment of the disclosure based on term vector.
Fig. 4 shows the flow chart that word-based feature in one embodiment of the disclosure carries out text classification training.
Fig. 5 shows the flow chart classified in one embodiment of the disclosure to the address of honouring an agreement of user.
Fig. 6 shows a kind of schematic diagram of the label information acquisition device provided in another embodiment of the disclosure.
Fig. 7 shows the schematic diagram of another label information acquisition device provided in another embodiment of the disclosure.
Fig. 8 show one embodiment of the disclosure offer be suitable for be used to realize that the structure of the electronic equipment of the embodiment of the present application is shown
It is intended to.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Attached drawing is only the disclosure
Schematic illustrations, be not necessarily drawn to scale.Identical appended drawing reference indicates same or similar part in figure, thus
Repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In mode.In the following description, many details are provided to provide and fully understand to embodiment of the present disclosure.So
And it will be appreciated by persons skilled in the art that one in the specific detail can be omitted with technical solution of the disclosure
Or more, or can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes
Known features, method, apparatus, realization, material or operation are to avoid a presumptuous guest usurps the role of the host and all aspects of this disclosure is made to become mould
Paste.
Some block diagrams shown in the drawings are functional entitys, not necessarily must be with physically or logically independent entity phase
It is corresponding.These functional entitys can be realized using software form, or in one or more hardware modules or integrated circuit in fact
These existing functional entitys, or these functions reality is realized in heterogeneous networks and/or processor device and/or microcontroller device
Body.
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
Attached drawing, the present invention is described in more detail.
In related embodiment of the invention, (it can usually be purchased by group, outside according to the direct consumer behavior of user in platform
Sell, make a reservation for, film, ticketing service etc.) certain attributes of user are portrayed, such as browse or traded in platform according to client
Film or the behaviors such as ticketing service can analyze the age for depicting user, hobby etc..But merely from customer transaction, browsing
The Financial Attribute that user is excavated in equal behaviors, is easy the limitation by platform category, not enough fills to the Financial Attribute excavation of user
Point.
Based on the above issues, some embodiments of the present disclosure provide a kind of label information acquisition methods, device, electronic equipment
And computer-readable medium, the address of honouring an agreement based on user, by natural language processing technique, by address structure of honouring an agreement, from
The house property value of user, occupation, living habit etc. are further obtained in structured message, to extract relatively stronger finance
Attribute.
Fig. 1 shows a kind of flow chart of the label information acquisition methods provided in one embodiment of the disclosure, including following step
It is rapid:
As shown in Figure 1, in step s 110, classify to the address of honouring an agreement of user, the classification knot for the address that obtains honouring an agreement
Fruit, wherein the address of honouring an agreement is the address that the user honours an agreement to order.
As shown in Figure 1, in the step s 120, the behavior of honouring an agreement for address of being honoured an agreement for described according to the user is in conjunction with described
Classification results are analyzed, and the label information of the user is obtained.
Fig. 2 is also shown the flow chart of another label information acquisition methods provided in one embodiment of the disclosure, including with
Lower step:
As shown in Fig. 2, classify in step S210 to the address of honouring an agreement of user, the classification knot for the address that obtains honouring an agreement
Fruit, wherein the address of honouring an agreement is the address that the user honours an agreement to order.
As shown in Fig. 2, attributive analysis is carried out to the classification results in conjunction with trade information database in step S220,
Obtain the attribute information of the address of honouring an agreement.
As shown in Fig. 2, the behavior of honouring an agreement for address of being honoured an agreement for described according to the user is in conjunction with described in step S230
Classification results and the attribute information are analyzed, and the label information of the user is obtained.
The difference is that, process shown in Fig. 2 is yet further still according to classification results combination industry with method flow shown in Fig. 1
Information database carries out attributive analysis, so as to according to user honour an agreement behavior combining classification result and attribute information to
Family label carries out depth analysis, obtains the label information of user.
By the label information acquisition methods in the present exemplary embodiment, by the address of honouring an agreement to user carry out classification and
Attribute Recognition is analyzed to obtain the label information of user, such as occupation, house property value, life in conjunction with the behavior of honouring an agreement of user
The relatively stronger Financial Attributes such as habit assess the consumption energy of user under the premise of not needing to obtain the sensitive information of user
Power.
It, will be to each step in the label information acquisition methods in the embodiment of the present disclosure below shown in Fig. 2 for process
It is further described.
In step S210, classify to the address of honouring an agreement of user, the classification results for the address that obtains honouring an agreement.
In one embodiment of the present disclosure, the address of honouring an agreement is the address honoured an agreement to order that user provides,
Such as user it is single at O2O when the orders such as the address for needing to honour an agreement to order, such as take-away, network about vehicle filled in involved in
Address is exactly address of honouring an agreement.Wherein include an address of honouring an agreement in a take-away order, includes two in a network about vehicle order
Item honours an agreement address (departure place and destination).Address of honouring an agreement in the present embodiment is mainly with the address of honouring an agreement taken out in order
Example, is equally applicable two addresses of honouring an agreement of departure place and destination in network about vehicle order.
In one embodiment of the present disclosure, classify described in step S210 to the address of honouring an agreement, honoured an agreement
The classification results of address can following two off-line model training by way of realize, specifically:
Off-line model training is carried out, mode can be with are as follows:
1) classification annotation is carried out to history address of honouring an agreement based on term vector, the mapping of obtain honouring an agreement address and classification is closed
System；
The classification results are obtained in conjunction with the mapping relations of honour an agreement address and the classification for the address of honouring an agreement；Or
Person is
2) word-based feature to the history honour an agreement address carry out Softmax training, obtain textual classification model；
The address of honouring an agreement is input to the textual classification model, exports the classification results.
Above-mentioned history address of honouring an agreement is the address honoured an agreement to History Order of multiple users in platform.
Fig. 3 shows the flow chart that classification annotation is carried out based on term vector, comprising the following steps:
As shown in figure 3, in step S301, honours an agreement from the history and extract trunk information in address.
It in one embodiment of the present disclosure, before this step further include honouring an agreement ground to the whole history obtained from platform
Location is filtered, and the mode of filtering includes the operation such as duplicate removal.
Such as an address of completely honouring an agreement can be such that
Shanghai City Changning road Zhao Feng square (4 buildings small southern part of the country opposite sugar cube small town)
Trunk information in above-mentioned address of honouring an agreement is exactly " Shanghai City Changning road Zhao Feng square ", in this step temporarily to including
Information in number is not considered.
As shown in figure 3, in step s 302, being segmented, being obtained multiplely by participle technique to the trunk information
Location participle.
In one embodiment of the present disclosure, for English address participle when using space as separator, in
The participle technique of literary address has very much, generally can choose and is divided based on dictionary pattern matching and hidden Markov model according to demand
Word.
Still by taking above-mentioned address of honouring an agreement as an example, segmented by the address obtained after step S202 are as follows:
Shanghai City Changning road Zhao Feng square
As shown in figure 3, the multiple address participle is converted to term vector in step S303.
In one embodiment of the present disclosure, right using word2vec technology (such as skipNgram model) in the step
Address participle is converted into term vector, and term vector technology is the context relation by word and word, training neural network model.
Still by taking above-mentioned address of honouring an agreement as an example, " Shanghai City " " Chang Ninglu " and " Zhao Feng square " each participle is segmented to address
A term vector can be obtained, finally these term vectors are added up and obtain this corresponding term vector of address text.
As shown in figure 3, in step s 304, being clustered to the term vector.
In one embodiment of the present disclosure, it can be clustered by kmeans, such as the address that will honour an agreement is polymerized to 1000 clusters.It is poly-
The number for the cluster that class obtains is set as needed, and the number of clusters of cluster is more, and the subsequent workload for needing to mark is bigger.
As shown in figure 3, in step S305, according to cluster result to the classification results of the trunk information of the address of honouring an agreement
Carry out corresponding classification annotation.
In one embodiment of the present disclosure, according to after cluster as a result, being carried out respectively to the address of honouring an agreement in each cluster
Mark.For example, manually being marked to the address of honouring an agreement of closest cluster centre in 1000 clusters, to honour an agreement ground to full dose
Location trunk is all labeled.For example, the classification annotation on Zhao Feng square is market, the classification annotation of Long Zhimeng hotel is hotel,
The classification annotation in the garden Kai Xinhao is house.
Fig. 4 shows the flow chart that word-based feature carries out text classification training, comprising the following steps:
As shown in figure 4, in step S401, the rule of correspondence of configuration address text and classification.
In one embodiment of the present disclosure, artificial dictionary can be configured, includes address text and classification in artificial dictionary
The rule of correspondence, format can be with are as follows: text -> classification.
As shown in figure 4, in step S402, history address of honouring an agreement is matched using multimode matching, if institute
It states history to honour an agreement address and the address text matches, then corresponding classification results is exported according to the rule of correspondence.
In one embodiment of the present disclosure, multimode matching is exactly whether judgment rule former piece has in the text of address and include
Relationship, this inclusion relation are exactly multimode matching, can handle some failures with the reason of above-mentioned rule of correspondence and multimode matching
Case or bad case (badcase), regular former piece are address texts, and consequent is exactly hotel, that is, is classified.
For example, the rule in artificial dictionary is hotel -> hotel, it is based on the rule of correspondence, if providing the hotel text * *,
Because just obtain " hotel * * " comprising " hotel " is classified as hotel.
As shown in figure 4, being segmented in step S403 to the address of honouring an agreement, and obtained participle is carried out polynary
Combination, the feature based on single participle or multiple participles carry out Softmax training, obtain the textual classification model.
In one embodiment of the present disclosure, for the corpus manually marked, to honouring an agreement, address is segmented, and is gone forward side by side
Row bigram (2 participles), trigram (2 participles) combination, based on unigram (single participle), bigram, trigram are special
Sign obtains textual classification model using Softmax training.
After training based on Fig. 3 and off-line model shown in Fig. 4, classify to the address of honouring an agreement of acquisition, which is
The process of one on-line prediction, Fig. 5 show the flow chart classified to the address of honouring an agreement of user, comprising the following steps:
As shown in figure 5, extracting the trunk information in address of honouring an agreement in step S501, passing through the address based on term vector
Mark available classification annotation.It is obtained by process shown in Fig. 3.
As shown in figure 5, being predicted in step S502 using word characteristic model, successively the trunk for address of honouring an agreement is believed
Part (such as part in bracket) except breath and trunk information is predicted, prediction result is obtained.For example, by using above-mentioned Fig. 4
Shown in process predicted, if it is possible to hit the rule in artificial dictionary, then directly according to the rule of correspondence return classification knot
Fruit, the classification results being otherwise trained with Softmax model.
During on-line prediction, the prediction technique of word-based vector sum cluster does not consider the content except trunk information (such as
Content in bracket) because the content distracter in bracket is more, influence cluster result.But off-line training mould when on-line prediction
Type can successively act on trunk information and non-trunk information, then take prediction result corresponding to the content in bracket, because
Address in bracket is more accurate specific.
For example, classification results when only considering trunk information are as follows:
Shanghai City Changning road Zhao Feng Square Mall
And if considering the non-trunk information in bracket, classification results are as follows:
Shanghai City Changning road Zhao Feng square (4 buildings small southern part of the country opposite sugar cube small town) incorporated business
Because sugar cube small town is many wound spaces, corresponding classification should be incorporated business, and no longer be market, can
It is more accurate to see below a kind of classification results.
In step S502 predict before, to honour an agreement address carry out noun of locality processing, such as address of honouring an agreement in if include " ...
The part on the noun of locality " opposite " is then ignored on opposite ".
In step S220, attributive analysis is carried out to the classification results in conjunction with trade information database, obtains the shoe
The about attribute information of address.
In one embodiment of the present disclosure, which carries out attribute to the classification results
Before analysis, further includes:
The step of constructing trade information database, specifically includes the following steps:
Firstly, being pre-processed to trade classification information；Secondly, according to pretreated trade classification information architecture industry
Information database.
Address and industry etc. are believed by way of pretreatment therein can be selected and purchased outside and/or public data crawls
Breath is obtained, is cleaned and structuring, and the information of triple form is obtained.
Constructing includes a plurality of information in obtained trade information database, includes: in each triplet information
Label；Classification results；Attribute information；
The classification results include: at least one of house, hospital, hotel, office building, Recreational places or more
It is a；The attribute information include: room rate, hospital category, Hotel Star, office building grade, in Recreational places grade extremely
Few one or more.
For example, the information in trade information database is as follows:
Building=the garden Kai Xinhao；House；Room rate=100000 yuan/square meter；
Hotel=Shangri-la；Hotel；Hotel Star=five-pointed star；
Hospital=Zhong Shan hospital；Hospital；Hospital category=Grade A hospital
In one embodiment of the present disclosure, the classification results are belonged in conjunction with trade information database in the step
Property analysis, obtain attribute information and specifically include:
By carrying out Forward Maximum Method to the information in the classification results and the trade information database, institute is obtained
State the corresponding attribute information in address of honouring an agreement.
Wherein one section of character string is exactly separated by the algorithm of Forward Maximum Method, wherein the limited length system separated,
Then the substring of separation is matched with the word in dictionary, next round matching, Zhi Daosuo is carried out if successful match
There is string processing to finish, substring is otherwise removed into a word from end, then matched, repeatedly.
Such as address of honouring an agreement are as follows:
The garden Kai Xinhao (12 building 306)
Obtaining classification results first is house, is then classified as house according to second in trade information database and sieve
Choosing, obtains the relevant entity of house, and then by way of Forward Maximum Method, matching obtains the entity comprising the garden Kai Xinhao,
The corresponding attribute in address of honouring an agreement, the i.e. entity of room rate information is obtained, i.e. room rate is 100000 yuan/square meter.
In step S230, according to the user for the address of honouring an agreement behavior of honouring an agreement in conjunction with the classification results and
The attribute information is analyzed, and the label information of user is obtained.
In one embodiment of the present disclosure, before which is made a concrete analysis of, further includes:
The user is obtained for the behavior of honouring an agreement of the address of honouring an agreement；Wherein the behavior of honouring an agreement includes: and carries out on working day
About number, nonworkdays honour an agreement number, date span of honouring an agreement and user at least one of markup information for address of honouring an agreement.
In one embodiment of the present disclosure, the behavior of honouring an agreement of the address of honouring an agreement is directed in conjunction with the classification according to user
As a result and/or the attribute information is analyzed, and the label information for obtaining user includes:
If the working day of user honours an agreement, number is more than or equal to first threshold, and the classification results are hospital, then obtain
The label information of the user is that occupation is medical worker；Or number is more than or equal to the second threshold if the nonworkdays of user is honoured an agreement
Value, and the classification results are house, and the room rate in the attribute information is more than or equal to third threshold value, then obtains the user
Label information be high-end cell.
Threshold value referenced by above-mentioned mapping process can be set as needed, such as working day honours an agreement number corresponding first
Threshold value can be set as 5 times, and the corresponding third threshold value of room rate then also needs to consider different cities and set.
The text and user extracted in given address of honouring an agreement according to user (works for the behavior of honouring an agreement of the address of honouring an agreement
Day honours an agreement number, and festivals or holidays honour an agreement number, and date span of honouring an agreement, user is to information such as the marks for address of honouring an agreement) it carries out analysis and reflects
It penetrates, obtains the label information of user.
Such as: if honouring an agreement address sort=office building, and address of honouring an agreement is place of working by user annotation, then speculates use
Family is white collar, i.e., label information is white collar.
If address sort=house, and developer=Wanke, and room rate=75635.0 yuan/square meter, and at this
Address is honoured an agreement date span > 1 year, and the address festivals or holidays honour an agreement number >=5, then speculate that user lives in high-end cell,
I.e. label is high-end cell.
For the crowd's truth labels for using address structure information of honouring an agreement to obtain, have in the amount of user, risk
Certain sequencing ability can be used as the strong Financial Attribute of user.
Based on above-mentioned process, the disclosure does not need to directly acquire the information of user, classifies to user address of honouring an agreement, can
Using judge user whether in residence (address sort of honouring an agreement is house) or place of working (address sort is office building or company
Enterprise) or other places honour an agreement.Then on the basis of classification, by the trade information database of construction and honour an agreement address into
Row association can further analyze the attribute information of the address of honouring an agreement of user, and combine its behavior of honouring an agreement (frequency of honouring an agreement, work
Day honours an agreement the frequency, and festivals or holidays honour an agreement the frequency, the time span etc. on date of honouring an agreement) obtain the label information of user, as house property value,
The information such as occupation and living habit, to extract the strong Financial Attribute of user.
In conclusion label information acquisition methods provided in this embodiment, are classified by the address of honouring an agreement to user
And Attribute Recognition, it is analyzed to obtain the label information of user, such as occupation, house property value, life in conjunction with the behavior of honouring an agreement of user
The relatively stronger Financial Attributes such as habit living, assess the consumption energy of user under the premise of not needing to obtain the sensitive information of user
Power.
Fig. 6 shows a kind of schematic diagram of the label information acquisition device provided in another embodiment of the disclosure, such as Fig. 6 institute
Show, which includes: address sort module 610 and label analysis module 620.
Address sort module 610 is configured to classify to the address of honouring an agreement of user, the classification results for the address that obtains honouring an agreement,
Wherein the address of honouring an agreement is the address that the user honours an agreement to order；Label analysis module 620 is configured to according to
User analyzes for the behavior of honouring an agreement of the address of honouring an agreement in conjunction with the classification results, obtains the label letter of the user
Breath.
The schematic diagram of another label information acquisition device provided in another embodiment of the disclosure, such as Fig. 7 is also shown in Fig. 7
Shown, which includes: address sort module 710, Attribute Recognition module 720 and label analysis module 730.
Address sort module 710 is configured to classify to the address of honouring an agreement of user, the classification results for the address that obtains honouring an agreement,
Wherein the address of honouring an agreement is the address honoured an agreement to order that the user provides；Attribute Recognition module 720 is configured to tie
It closes trade information database and attributive analysis is carried out to the classification results, obtain the attribute information of the address of honouring an agreement；Label point
Analysis module 730 is configured to be directed to the behavior of honouring an agreement of the address of honouring an agreement according to the user in conjunction with the classification results and the category
Property information is analyzed, and the label information of user is obtained.
The function of modules is referring to the associated description in above method embodiment in the device, and details are not described herein again.
In conclusion the label information acquisition device in the present embodiment, by the address of honouring an agreement to user carry out classification and
Attribute Recognition is analyzed to obtain the label information of user, such as occupation, house property value, life in conjunction with the behavior of honouring an agreement of user
The relatively stronger Financial Attributes such as habit assess the consumption energy of user under the premise of not needing to obtain the sensitive information of user
Power.
On the other hand, the disclosure additionally provides a kind of electronic equipment, including processor and memory, and memory storage is used for
The operational order of above-mentioned processor control following methods:
Classify to the address of honouring an agreement of user, the classification results for the address that obtains honouring an agreement, wherein described honour an agreement address as institute
State the address that user honours an agreement to order；The behavior of honouring an agreement of the address of honouring an agreement is directed in conjunction with the classification according to the user
As a result it is analyzed, obtains the label information of user.Or
Classify to the address of honouring an agreement of user, the classification results for the address that obtains honouring an agreement, wherein described honour an agreement address as institute
State the address that user honours an agreement to order；Attributive analysis is carried out to the classification results in conjunction with trade information database, is obtained
The attribute information of the address of honouring an agreement；The behavior of honouring an agreement of the address of honouring an agreement is directed in conjunction with the classification results according to the user
It is analyzed with the attribute information, obtains the label information of the user.
Below with reference to Fig. 8, it illustrates the computer systems 800 for the electronic equipment for being suitable for being used to realize the embodiment of the present application
Structural schematic diagram.Electronic equipment shown in Fig. 8 is only an example, function to the embodiment of the present application and should not use model
Shroud carrys out any restrictions.
As shown in figure 8, computer system 800 includes central processing unit (CPU) 801, it can be read-only according to being stored in
Program in memory (ROM) 802 or be loaded into the program in random access storage device (RAM) 803 from storage section 805 and
Execute various movements appropriate and processing.In RAM 803, also it is stored with system 800 and operates required various programs and data.
CPU 801, ROM 802 and RAM 803 are connected with each other by bus 804.Input/output (I/O) interface 805 is also connected to always
Line 804.
I/O interface 805 is connected to lower component: the importation 806 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 808 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 808 including hard disk etc.；
And the communications portion 809 of the network interface card including LAN card, modem etc..Communications portion 809 via such as because
The network of spy's net executes communication process.Driver 810 is also connected to I/O interface 805 as needed.Detachable media 811, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 810, in order to read from thereon
Computer program be mounted into storage section 808 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 809, and/or from detachable media
811 are mounted.When the computer program is executed by central processing unit (CPU) 801, executes and limited in the system of the application
Above-mentioned function.
It should be noted that computer-readable medium shown in the application can be computer-readable signal media or meter
Calculation machine readable medium either the two any combination.Computer-readable medium for example may be-but not limited to-
Electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.It is computer-readable
The more specific example of medium can include but is not limited to: have electrical connection, the portable computer magnetic of one or more conducting wires
Disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or sudden strain of a muscle
Deposit), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or above-mentioned appoint
The suitable combination of meaning.In this application, computer-readable medium can be any tangible medium for including or store program, the journey
Sequence can be commanded execution system, device or device use or in connection.And in this application, it is computer-readable
Signal media may include in a base band or as carrier wave a part propagate data-signal, wherein carrying computer can
The program code of reading.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal, optical signal or
Above-mentioned any appropriate combination.Computer-readable signal media can also be any calculating other than computer-readable medium
Machine readable medium, the computer-readable medium can be sent, propagated or transmitted for by instruction execution system, device or device
Part uses or program in connection.The program code for including on computer-readable medium can use any Jie appropriate
Matter transmission, including but not limited to: wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor packet
Include transmission unit, acquiring unit, determination unit and first processing units.Wherein, the title of these units is under certain conditions simultaneously
The restriction to the unit itself is not constituted, for example, transmission unit is also described as " sending picture to the server-side connected
The unit of acquisition request ".
On the other hand, the disclosure additionally provides a kind of computer-readable medium, which can be above-mentioned
Included in equipment described in embodiment；It is also possible to individualism, and without in the supplying equipment.Above-mentioned computer can
It reads medium and carries one or more program, when said one or multiple programs are executed by the equipment, so that this
Equipment comprises the following methods:
Classify to the address of honouring an agreement of user, the classification results for the address that obtains honouring an agreement, wherein described honour an agreement address to use
The address honoured an agreement to order that family provides；The behavior of honouring an agreement of the address of honouring an agreement is directed in conjunction with described point according to the user
Class result is analyzed, and the label information of the user is obtained.Or
Classify to the address of honouring an agreement of user, the classification results for the address that obtains honouring an agreement, wherein described honour an agreement address as institute
State the address that user honours an agreement to order；Attributive analysis is carried out to the classification results in conjunction with trade information database, is obtained
The attribute information of the address of honouring an agreement；The behavior of honouring an agreement of the address of honouring an agreement is directed in conjunction with the classification results according to the user
It is analyzed with the attribute information, obtains the label information of the user.
It will be clearly understood that the present disclosure describes how to form and use particular example, but the principle of the disclosure is not limited to
These exemplary any details.On the contrary, the introduction based on disclosure disclosure, these principles can be applied to many other
Embodiment.
It is particularly shown and described the illustrative embodiments of the disclosure above.It should be appreciated that the disclosure is unlimited
In detailed construction described herein, set-up mode or implementation method；On the contrary, disclosure intention covers included in appended claims
Spirit and scope in various modifications and equivalence setting.
Claims (14)
1. a kind of label information acquisition methods characterized by comprising
Classify to the address of honouring an agreement of user, the classification results for the address that obtains honouring an agreement, wherein the address of honouring an agreement is the use
The address that family honours an agreement to order；
It is analyzed for the behavior of honouring an agreement of the address of honouring an agreement in conjunction with the classification results according to the user, obtains the use
The label information at family.
2. label information acquisition methods according to claim 1, which is characterized in that honoured an agreement according to the user for described
The behavior of honouring an agreement of address is analyzed in conjunction with the classification results, and the label information for obtaining the user includes:
Attributive analysis is carried out to the classification results in conjunction with trade information database, obtains the attribute information of the address of honouring an agreement；
It is carried out for the behavior of honouring an agreement of the address of honouring an agreement in conjunction with the classification results and the attribute information according to the user
Analysis, obtains the label information of the user.
3. label information acquisition methods according to claim 1, which is characterized in that described to divide the address of honouring an agreement
The classification results of class, the address that obtains honouring an agreement include:
Classification annotation is carried out to history address of honouring an agreement based on term vector, the mapping relations of obtain honouring an agreement address and classification, wherein institute
Stating history address of honouring an agreement is the address honoured an agreement to History Order of multiple users in platform；
The classification results are obtained in conjunction with the mapping relations of honour an agreement address and the classification for the address of honouring an agreement.
4. label information acquisition methods according to claim 3, which is characterized in that honoured an agreement address based on term vector to history
Carrying out classification annotation includes:
It honours an agreement from the history and extracts trunk information in address；
The trunk information is segmented by participle technique, obtains multiple address participles；
The multiple address participle is converted to term vector；
The term vector is clustered；
Corresponding classification annotation is carried out according to classification results of the cluster result to the trunk information of the address of honouring an agreement.
5. label information acquisition methods according to claim 1, which is characterized in that described to divide the address of honouring an agreement
The classification results of class, the address that obtains honouring an agreement include:
Word-based feature to history honour an agreement address carry out Softmax training, textual classification model is obtained, wherein the history is honoured an agreement
Address is the address that multiple users in platform honour an agreement to History Order；
The address of honouring an agreement is input to the textual classification model, exports the classification results.
6. label information acquisition methods according to claim 5, which is characterized in that word-based feature honours an agreement address to history
Carrying out Softmax training includes:
The rule of correspondence of configuration address text and classification；
History address of honouring an agreement is matched using multimode matching, address and the address text if the history is honoured an agreement
Matching then exports corresponding classification results according to the rule of correspondence；
The address of honouring an agreement is segmented, and multiplexed combination is carried out to obtained participle, based on single participle or multiple participles
Feature carry out Softmax training, obtain the textual classification model.
7. label information acquisition methods according to claim 2, which is characterized in that in conjunction with trade information database to described
Classification results carry out before attributive analysis, further includes:
Trade classification information is pre-processed；
According to pretreated trade classification information architecture trade information database；
Wherein include a plurality of information in the trade information database, includes: in information described in each
Label；Classification results；Attribute information；
The classification results include: at least one of house, hospital, hotel, office building, Recreational places or multiple；
The attribute information include: room rate, hospital category, Hotel Star, office building grade, in Recreational places grade extremely
Few one or more.
8. label information acquisition methods according to claim 7, which is characterized in that in conjunction with trade information database to described
Classification results carry out attributive analysis, obtain attribute information:
By carrying out Forward Maximum Method to the information in the classification results and the trade information database, the shoe is obtained
The about corresponding attribute information in address.
9. label information acquisition methods according to claim 2, which is characterized in that honoured an agreement according to the user for described
Before the behavior of honouring an agreement of address is analyzed in conjunction with the classification results, further includes:
The user is obtained for the behavior of honouring an agreement of the address of honouring an agreement；
Wherein the behavior of honouring an agreement includes: that honour an agreement on working day number, nonworkdays is honoured an agreement number, date span of honouring an agreement and the use
Markup information at least one of of the family to address of honouring an agreement.
10. label information acquisition methods according to claim 9, which is characterized in that be directed to the shoe according to the user
The behavior of honouring an agreement of about address is analyzed in conjunction with the classification results, and the label information for obtaining the user includes:
If the working day of the user honours an agreement, number is more than or equal to first threshold, and the classification results are hospital, then obtain
The label information of the user is that occupation is medical worker.
11. label information acquisition methods according to claim 9, which is characterized in that be directed to the shoe according to the user
The behavior of honouring an agreement of about address is analyzed in conjunction with the classification results and the attribute information, obtains the label information of the user
Include:
If the nonworkdays of the user is honoured an agreement, number is more than or equal to second threshold, and the classification results are house, and institute
The room rate stated in attribute information is more than or equal to third threshold value, then the label information for obtaining the user is high-end cell.
12. a kind of label information acquisition device characterized by comprising
Address sort module is configured to classify to the address of honouring an agreement of user, the classification results for the address that obtains honouring an agreement, wherein institute
Stating address of honouring an agreement is the address that the user honours an agreement to order；
Label analysis module is configured to be directed to the behavior of honouring an agreement of the address of honouring an agreement according to the user in conjunction with the classification results
It is analyzed, obtains the label information of the user.
13. a kind of electronic equipment characterized by comprising
Processor；
Memory, instruction of the storage for the processor control such as described in any item method and steps of claim 1-11.
14. a kind of computer-readable medium, is stored thereon with computer executable instructions, which is characterized in that the executable finger
Such as claim 1-11 described in any item method and steps are realized when order is executed by processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811333350.4A CN109492103B (en) | 2018-11-09 | 2018-11-09 | Label information acquisition method and device, electronic equipment and computer readable medium |
| CA3060822A CA3060822C (en) | 2018-11-09 | 2019-11-01 | Label information acquistion method and apparatus, electronic device and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811333350.4A CN109492103B (en) | 2018-11-09 | 2018-11-09 | Label information acquisition method and device, electronic equipment and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109492103A true CN109492103A (en) | 2019-03-19 |
| CN109492103B CN109492103B (en) | 2019-12-17 |
Family
ID=65694177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811333350.4A Active CN109492103B (en) | 2018-11-09 | 2018-11-09 | Label information acquisition method and device, electronic equipment and computer readable medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109492103B (en) |
| CA (1) | CA3060822C (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110213239A (en) * | 2019-05-08 | 2019-09-06 | 阿里巴巴集团控股有限公司 | Suspicious transaction message generation method, device and server |
| CN111310462A (en) * | 2020-02-07 | 2020-06-19 | 北京三快在线科技有限公司 | User attribute determination method, device, equipment and storage medium |
| CN111723226A (en) * | 2020-06-14 | 2020-09-29 | 黄雨勤 | Information management method based on big data and Internet and artificial intelligence cloud server |
| CN111861046A (en) * | 2019-04-02 | 2020-10-30 | 南京大学 | Intelligent patent value evaluation system based on big data and deep learning |
| CN111966730A (en) * | 2020-10-23 | 2020-11-20 | 北京淇瑀信息科技有限公司 | Risk prediction method and device based on permanent premises and electronic equipment |
| CN112434154A (en) * | 2019-08-26 | 2021-03-02 | 北京星选科技有限公司 | Object processing method and device, electronic equipment and storage medium |
| CN116521827A (en) * | 2023-05-19 | 2023-08-01 | 北京百度网讯科技有限公司 | Geographic position place category determination method and device, electronic equipment and medium |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417251B (en) * | 2020-11-30 | 2024-10-11 | 华能大理风力发电有限公司 | Transaction information retrieval method and device based on wind power bidding |
| CN112488103B (en) * | 2020-11-30 | 2024-10-15 | 上海寻梦信息技术有限公司 | Address information extraction method, model training method and related equipment |
| CN112561479B (en) * | 2020-12-16 | 2023-09-19 | 中国平安人寿保险股份有限公司 | Intelligent decision-making-based enterprise personnel increasing method and device and computer equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160277492A1 (en) * | 2015-03-16 | 2016-09-22 | International Business Machines Corporation | Image file transmission |
| US20180040059A1 (en) * | 2016-08-05 | 2018-02-08 | Accenture Global Solutions Limited | Social network data processing and profiling |
| CN108287858A (en) * | 2017-03-02 | 2018-07-17 | 腾讯科技（深圳）有限公司 | The semantic extracting method and device of natural language |
| CN108287850A (en) * | 2017-01-10 | 2018-07-17 | 阿里巴巴集团控股有限公司 | The optimization method and device of textual classification model |
| CN108345596A (en) * | 2017-01-22 | 2018-07-31 | 分众(中国)信息技术有限公司 | Building information converged services platform |
| CN108711004A (en) * | 2018-05-14 | 2018-10-26 | 北京京东金融科技控股有限公司 | Methods of risk assessment and device and computer readable storage medium |
-
2018
- 2018-11-09 CN CN201811333350.4A patent/CN109492103B/en active Active
-
2019
- 2019-11-01 CA CA3060822A patent/CA3060822C/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160277492A1 (en) * | 2015-03-16 | 2016-09-22 | International Business Machines Corporation | Image file transmission |
| US20180040059A1 (en) * | 2016-08-05 | 2018-02-08 | Accenture Global Solutions Limited | Social network data processing and profiling |
| CN108287850A (en) * | 2017-01-10 | 2018-07-17 | 阿里巴巴集团控股有限公司 | The optimization method and device of textual classification model |
| CN108345596A (en) * | 2017-01-22 | 2018-07-31 | 分众(中国)信息技术有限公司 | Building information converged services platform |
| CN108287858A (en) * | 2017-03-02 | 2018-07-17 | 腾讯科技（深圳）有限公司 | The semantic extracting method and device of natural language |
| CN108711004A (en) * | 2018-05-14 | 2018-10-26 | 北京京东金融科技控股有限公司 | Methods of risk assessment and device and computer readable storage medium |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861046A (en) * | 2019-04-02 | 2020-10-30 | 南京大学 | Intelligent patent value evaluation system based on big data and deep learning |
| CN111861046B (en) * | 2019-04-02 | 2023-12-29 | 南京大学 | Intelligent patent value assessment system based on big data and deep learning |
| CN110213239A (en) * | 2019-05-08 | 2019-09-06 | 阿里巴巴集团控股有限公司 | Suspicious transaction message generation method, device and server |
| CN110213239B (en) * | 2019-05-08 | 2021-06-01 | 创新先进技术有限公司 | Suspicious transaction message generation method and device and server |
| CN112434154A (en) * | 2019-08-26 | 2021-03-02 | 北京星选科技有限公司 | Object processing method and device, electronic equipment and storage medium |
| CN111310462A (en) * | 2020-02-07 | 2020-06-19 | 北京三快在线科技有限公司 | User attribute determination method, device, equipment and storage medium |
| CN111723226A (en) * | 2020-06-14 | 2020-09-29 | 黄雨勤 | Information management method based on big data and Internet and artificial intelligence cloud server |
| CN111966730A (en) * | 2020-10-23 | 2020-11-20 | 北京淇瑀信息科技有限公司 | Risk prediction method and device based on permanent premises and electronic equipment |
| CN116521827A (en) * | 2023-05-19 | 2023-08-01 | 北京百度网讯科技有限公司 | Geographic position place category determination method and device, electronic equipment and medium |
| CN116521827B (en) * | 2023-05-19 | 2024-07-23 | 北京百度网讯科技有限公司 | Geographic position place category determination method and device, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CA3060822A1 (en) | 2020-05-09 |
| CN109492103B (en) | 2019-12-17 |
| CA3060822C (en) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492103A (en) | Label information acquisition methods, device, electronic equipment and computer-readable medium | |
| CN108089843B (en) | Intelligent bank enterprise-level demand management system | |
| WO2022057658A1 (en) | Method and apparatus for training recommendation model, and computer device and storage medium | |
| CN113822494A (en) | Risk prediction method, device, equipment and storage medium | |
| CN109241524A (en) | Semantic analysis method and device, computer readable storage medium, electronic equipment | |
| CN109614550A (en) | Public sentiment monitoring method, device, computer equipment and storage medium | |
| US20220100963A1 (en) | Event extraction from documents with co-reference | |
| US20150286943A1 (en) | Decision Making and Planning/Prediction System for Human Intention Resolution | |
| CN114648392B (en) | Product recommendation method and device based on user portrait, electronic equipment and medium | |
| CN109740642A (en) | Invoice category recognition methods, device, electronic equipment and readable storage medium storing program for executing | |
| CN113220999B (en) | User characteristic generation method and device, electronic equipment and storage medium | |
| CN109582788A (en) | Comment spam training, recognition methods, device, equipment and readable storage medium storing program for executing | |
| CN113592605B (en) | Product recommendation method, device, equipment and storage medium based on similar products | |
| CN113051914A (en) | Enterprise hidden label extraction method and device based on multi-feature dynamic portrait | |
| CN112926308B (en) | Method, device, equipment, storage medium and program product for matching text | |
| CN111143534A (en) | Method and device for extracting brand name based on artificial intelligence and storage medium | |
| CN115293603A (en) | Task allocation method and device, electronic equipment and computer readable storage medium | |
| CN113051911A (en) | Method, apparatus, device, medium, and program product for extracting sensitive word | |
| CN113704420A (en) | Method and device for identifying role in text, electronic equipment and storage medium | |
| CN114140947A (en) | Interface display method and device, electronic equipment, storage medium and program product | |
| CN116402166A (en) | Training method and device of prediction model, electronic equipment and storage medium | |
| CN113569578B (en) | User intention recognition method and device and computer equipment | |
| CN114780600A (en) | Flight searching method, system, equipment and storage medium | |
| CN114492408A (en) | Credit certificate auditing method and device, electronic equipment and storage medium | |
| CN111241273A (en) | Text data classification method and device, electronic equipment and computer readable medium |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200624 Address after: Room 301, building 2, No. 18, Tianshan West Road, Changning District, Shanghai, 200335 Patentee after: Shanghai Liangxin Technology Co., Ltd Address before: 100083 Beijing Haidian District North Fourth Ring Road West, No. 9 2106-030 Patentee before: BEIJING SANKUAI ONLINE TECHNOLOGY Co.,Ltd. |