CN111367942B - Address book retrieval method and device - Google Patents
Address book retrieval method and device Download PDFInfo
- Publication number
- CN111367942B CN111367942B CN202010236187.0A CN202010236187A CN111367942B CN 111367942 B CN111367942 B CN 111367942B CN 202010236187 A CN202010236187 A CN 202010236187A CN 111367942 B CN111367942 B CN 111367942B
- Authority
- CN
- China
- Prior art keywords
- address book
- user
- relationship graph
- retrieval
- word
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/2433—Query languages
- G06F16/2448—Query languages for particular applications; for extensibility, e.g. user defined types
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
According to the address book searching method and device, the multidimensional attribute characteristics of each word segmentation are obtained through splitting the to-be-searched entry, then the multidimensional attribute characteristics are input into the combined decision tree model, the decision tree model predicts the query purpose of a user, intelligent error correction is achieved, more accurate personnel query is provided, model tuning is continuously performed by combining the machine learning function of the decision tree model, manual rule intervention is reduced, universal and convenient basic service is provided, and the use experience of a system is improved.
Description
Technical Field
The invention relates to the technical field of address book retrieval, in particular to an address book retrieval method and an address book retrieval device.
Background
The enterprise internal address book is mainly used for communication among staff in the working process, and in most cases, the contact person range of the staff is relatively stable in a certain time, and the contact person range of the staff can be changed greatly along with the change of the posts. Especially, under the condition that a group enterprise has hundreds of thousands of staff, the conditions of staff post adjustment, communication, borrowing and the like often occur, and the conditions of the name of the staff, the rare words and the nationality are relatively prominent. Therefore, it is difficult to reflect the communication relationship after the work change in time by a single personal relationship map. Furthermore, the protection hierarchy of employee privacy information (mobile phones, home phones, emergency contact information, etc.) is relatively complex. How to improve the accuracy of the enterprise address book and improve the use experience of the address book so as to smoothly develop the work is a problem to be solved urgently.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an address book searching method and device.
In order to solve the technical problems, the invention provides the following technical scheme:
in one aspect of the present invention, there is provided an address book searching method, the address book including a plurality of content classifications, the address book searching method including:
splitting the entry to be checked input by the user to obtain a plurality of word segments; each of the tokens belongs to one of the content categories, and each of the tokens contains a multi-dimensional attribute feature; each dimension of the attribute feature includes a plurality of different feature contents;
inputting each word segment into a plurality of decision tree models to obtain the corresponding relation of the characteristic content, the content classification and the probability under each attribute characteristic;
determining the content classification of each word segmentation based on each corresponding relation, and generating a retrieval combination;
and searching in the address book based on the searching combination.
In a preferred embodiment, the content classification comprises: name, organization name, post name, phone number.
In a preferred embodiment, the attribute features include:
character length, word type and the sequence of the word to be checked in the entry where the word is located.
In a preferred embodiment, further comprising:
establishing a plurality of initial decision tree models;
and training each initial decision tree model by using the query terms of the marked word segmentation content classification to obtain a plurality of decision tree models.
In a preferred embodiment, the determining, based on each of the correspondence, the content classification to which each word belongs includes:
generating average probability of all characteristic contents under each content category according to each corresponding relation;
and selecting the content classification with the maximum corresponding average probability as the content classification corresponding to the word segmentation.
In a preferred embodiment, the searching in the address book based on the searching combination includes:
searching a plurality of personnel information meeting the content classification limited by the search combination according to the search combination;
according to the user identity of the entry to be checked, determining a first serial number of each piece of personnel information in a personal relationship graph corresponding to the user and a second serial number in a group relationship graph;
generating an arrangement sequence number of each piece of personnel information relative to the user according to the first sequence number, the second sequence number, the personal relationship graph weight and the group relationship graph weight corresponding to the user;
And sequentially displaying the personnel information to be displayed according to the generated arrangement serial numbers.
In a preferred embodiment, searching in the address book based on the searching combination further comprises:
determining the viewing authority of the user according to the user identity of the entry to be checked;
determining a part which is not displayed in the personnel information according to the viewing authority;
correspondingly, the personnel information in the user viewing authority is displayed when the sequential display is carried out.
In a preferred embodiment, the generating the ranking number of each piece of personnel information relative to the user includes:
calculating the arrangement sequence number of the user according to a calculation formula; wherein, the calculation formula is:
m＝a×i+b×j
wherein a is a personal relationship graph weight, and b is a group relationship graph weight; i is personal relationship graph ranking number, b is group relationship graph ranking number, and m is ranking number.
In another aspect of the present invention, there is provided an address book searching apparatus, the address book including a plurality of content classifications, the address book searching apparatus comprising:
the word segmentation splitting module splits the entry to be checked input by the user to obtain a plurality of segmented words; each of the tokens belongs to one of the content categories, and each of the tokens contains a multi-dimensional attribute feature; each dimension of the attribute feature includes a plurality of different feature contents;
The word segmentation input module is used for inputting each word segmentation into a plurality of decision tree models to obtain the corresponding relation of the characteristic content, the content classification and the probability under each attribute characteristic;
the search combination generation module is used for determining the content classification of each word segment based on each corresponding relation to generate a search combination;
and the searching module is used for searching in the address book based on the searching combination.
In a preferred embodiment, the content classification comprises: name, organization name, post name, phone number.
In a preferred embodiment, the attribute features include:
character length, word type and the sequence of the word to be checked in the entry where the word is located.
In a preferred embodiment, further comprising:
the model building module is used for building a plurality of initial decision tree models;
and the model training module is used for training each initial decision tree model by utilizing the query vocabulary entries of the marked word segmentation content classification to obtain the plurality of decision tree models.
In a preferred embodiment, the search combination generation module includes:
the average probability generating unit generates average probability of all characteristic contents under each content category according to each corresponding relation;
And the content classification selection unit selects the content classification with the maximum corresponding average probability as the content classification corresponding to the word segmentation.
In a preferred embodiment, the retrieval module comprises:
a personnel information retrieval unit for retrieving a plurality of personnel information conforming to the content classification defined by the retrieval combination according to the retrieval combination;
a serial number determining unit, configured to determine, according to a user identity input to the entry to be checked, a first serial number of each piece of personal information in a personal relationship graph corresponding to the user and a second serial number of each piece of personal information in a group relationship graph;
an arrangement sequence number generating unit, configured to generate an arrangement sequence number of each piece of personnel information relative to the user according to the first sequence number, the second sequence number, and the personal relationship graph weight and the group relationship graph weight corresponding to the user;
and the ordering display unit is used for sequentially displaying the personnel information to be displayed according to the generated ordering sequence number.
In a preferred embodiment, the retrieval module further comprises:
the permission determining unit is used for determining the viewing permission of the user according to the user identity of the entry to be checked;
the screening unit is used for determining the part which is not displayed in the personnel information according to the viewing authority;
Correspondingly, the sequencing display unit displays the personnel information in the user viewing authority when sequentially displaying.
In a preferred embodiment, the arrangement sequence number generating unit calculates the arrangement sequence number of the user according to a calculation formula; wherein, the calculation formula is:
m＝a×i+b×j
wherein a is a personal relationship graph weight, and b is a group relationship graph weight; i is personal relationship graph ranking number, b is group relationship graph ranking number, and m is ranking number.
In yet another aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the address book retrieval method when executing the program.
In yet another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor, implements an address book retrieval method.
According to the address book searching method and device, the multi-dimensional attribute characteristics of each word are obtained through splitting the to-be-checked entry, then the multi-dimensional attribute characteristics are input into the combined decision tree model, the decision tree model predicts the query purpose of a user, intelligent error correction is achieved, more accurate personnel query is provided, meanwhile, model tuning is continuously carried out by combining the machine learning function of the decision tree model, manual rule intervention is reduced, universal and convenient basic service is provided, and the use experience of a system is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an address book searching method according to an embodiment of the present invention.
Fig. 2 is one of the specific flowcharts of step S4 in fig. 1.
Fig. 3 is a second flowchart of step S4 in fig. 1.
Fig. 4 is a schematic diagram of screening personnel information according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of an address book searching device according to an embodiment of the invention.
FIG. 6 is a schematic diagram of the search module in FIG. 5.
FIG. 7 is a second schematic diagram of the search module in FIG. 5.
FIG. 8 is a schematic diagram of a personal relationship graph in an embodiment of the present invention.
FIG. 9 is a schematic diagram of a group relationship graph in an embodiment of the present invention.
Fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Considering that the address book in the enterprise is complex, and the contact range is continuously changed due to personnel variation, the conditions of staff post adjustment, communication, borrowing and the like often occur, and the conditions of the name of staff, the rare words and the nationality are relatively prominent. Firstly, splitting an entry to be checked input by a user to obtain a plurality of word segments; then inputting each word into a plurality of decision tree models to obtain the corresponding relation of the characteristic content, the content classification and the probability under each attribute characteristic; determining the content classification of each word segmentation based on each corresponding relation, and generating a retrieval combination; and finally, searching in the address book based on the searching combination, so as to realize the inquiry purpose of a predicted user, realize intelligent error correction, provide more accurate personnel inquiry, simultaneously combine the machine learning function of the decision tree model to continuously perform model tuning, reduce manual rule intervention, provide universal and convenient basic service and improve the use experience of the system.
In one or more embodiments of the present invention, as shown in fig. 1, an address book searching method, where the address book includes a plurality of content classifications, includes:
S1: splitting the entry to be checked input by the user to obtain a plurality of word segments; each of the tokens belongs to one of the content categories, and each of the tokens contains a multi-dimensional attribute feature; each dimension of the attribute feature includes a plurality of different feature contents.
In the invention, for some enterprise address books, the content classification includes name, organization name, post name, phone number.
Further, the attribute features include: character length, word type and the sequence of the word to be checked in the entry where the word is located.
In general, the term to be checked input by the user can be split into 2 or 3 word segments, and the word segments are identified by a word identification mode, for example, the term to be checked is: su Dajiang by the human resources department. The human resource part and Su Da can be identified by word recognition.
In a preferred embodiment, the word recognition method can recognize the word segmentation based on machine learning to improve recognition accuracy.
S2: and inputting each word into a plurality of decision tree models to obtain the corresponding relation of the characteristic content, the content classification and the probability under each attribute characteristic.
Specifically, a plurality of decision tree models are constructed based on a random forest algorithm, and each model comprises a corresponding relation among characteristic content, content classification and probability under an attribute characteristic.
In the present invention, the feature content is each specific representation of the attribute feature, for example, for the attribute feature of the character length, the feature content may be 0-8 characters, 9-20 characters, etc., and for the feature content of the word type, it may be Chinese characters, letters, numbers, etc.
The corresponding relation between the characteristic content and the content classification under each attribute characteristic and the probability can be obtained through the step S2, namely the probability value corresponding to each characteristic content and each characteristic content classification can be obtained through a searching mode.
In some embodiments, the correspondence may be stored in the computer device through a lookup table.
S3: and determining the content classification to which each word belongs based on each corresponding relation, and generating a retrieval combination.
In some specific embodiments, step S3 includes:
s31: and generating average probability of all the characteristic contents under each content category according to each corresponding relation.
For example, for "Su Dajiang", "Su Dajiang" the word type is kanji, the number of characters is 2-8, for the entry to be examined: "Su Da" is a powerful resource section, and is located at 1.
In the decision tree model, the probability of Chinese characters under the name content classification is 33%, the probability of characters 0-8 is 65%, and the probability of position 1 is 40%, and the average probability is (33% +65% +40%)/3=138%/3=46%).
S32: and selecting the content classification with the maximum corresponding average probability as the content classification corresponding to the word segmentation.
For another example, "Su Dajiang" has an average probability of 19% for organizations, 27% for posts, and 8% for phones, and the name with the highest probability (46%) is selected as the content classification of the word, and "Su Dajiang" is determined to be the name. Thus, a search combination can be obtained:
name= 'Su Dajiang' and Dept= 'part of human resources'
Or
Name= 'Su Dajiang' and org= 'part of human resources'
After the above condition splitting is completed, it can be obtained that the user intends to search for "user named Su Da strong under the agency of human resources" or "user named Su Da strong under the agency of human resources".
S4: and searching in the address book based on the searching combination.
According to the searching combination, searching can be performed in the address book.
In a preferred embodiment, step S4 does not use only personal relationship maps for searching, but also complex searching in combination with group relationship maps.
In this embodiment, as shown in fig. 2, step S4 specifically includes:
s41: and searching a plurality of personnel information meeting the content classification limited by the search combination according to the search combination.
Because the enterprise address book includes a large number of renamed users, for example, "Su Da strong" may include a plurality of users with strong names Su Da, this step retrieves users who meet each of the word-defining content categories.
S42: and determining a first serial number of each personal information in a personal relationship graph corresponding to the user and a second serial number in a group relationship graph according to the user identity of the input entry to be checked.
In the present invention, as shown in fig. 8, a personal relationship graph is established by collecting click objects of users, and adjusting the distance of nodes in the personal relationship graph according to the communication frequency, and the adjusted personal relationship graph is stored in the cloud or local.
As shown in fig. 9, the group relationship map is obtained by combining a clustering algorithm with a personal relationship map and correcting the personal relationship map by using a graph group detection algorithm.
Specifically, each piece of personal information is ordered in the corresponding personal relationship graph and group relationship graph according to relationship distance. The personal relationship map and the group relationship map of the user are searched for.
S43: and generating an arrangement sequence number of each piece of personnel information relative to the user according to the first sequence number, the second sequence number, the personal relationship graph weight and the group relationship graph weight corresponding to the user.
In some embodiments, the ranking number of the user may be calculated according to a calculation formula; wherein, the calculation formula is:
m＝a×i+b×j
wherein a is a personal relationship graph weight, and b is a group relationship graph weight; i is personal relationship graph ranking number, b is group relationship graph ranking number, and m is ranking number.
For example: user a is a basic manager credit officer group, and for his search results M, the ranking strategy is: { M } × (personal relationship profile×0.7+group relationship profile×0.3). When the user a is a decision maker group of the headquarter manager, his ranking strategy may be adjusted as follows: { M } × (personal relationship profile×0.2+group relationship profile×0.8).
S44: and sequentially displaying the personnel information to be displayed according to the generated arrangement serial numbers.
Through the embodiment, the personal relationship map and the group relationship map are combined, so that the requirement that the single relationship map cannot reflect the change of the group communication relationship after the individual attribute of the user is changed can be better solved.
In a further preferred embodiment, as shown in fig. 3, step S4 further comprises:
s45: determining the viewing authority of the user according to the user identity of the entry to be checked;
S46: determining a part which is not displayed in the personnel information according to the viewing authority;
correspondingly, step S44 displays the personnel information in the user viewing authority when the sequential display is performed.
For example, the result screening is completed in combination with privacy policies inside the enterprise, for example, the privacy of a manager at a higher level is protected from random harassment, the personal family contact of staff is protected from leakage, and the like. The condition information of the staff in the enterprise for privacy protection comprises posts, institutions, departments, job positions and the like. As shown in fig. 4: the left set is the visible information set of the current user, the right set is the search result set, and the intersecting part (black filling) of the two sets is the reserved item after result screening.
In addition, the decision tree model may be built online or offline in the present invention, that is, the step of building the model may be included in the implementation step of the present invention, or may be built in advance away from the implementation step of the present invention, which is not limited in this aspect of the present invention.
Specifically, the step of building a decision tree model specifically includes:
s01: establishing a plurality of initial decision tree models;
s02: and training each initial decision tree model by using the query terms of the marked word segmentation content classification to obtain a plurality of decision tree models.
From the above description, it can be seen that the address book searching method provided by one aspect of the present invention obtains the multidimensional attribute characteristics of each word segment by splitting the entry to be searched, and then inputs the multidimensional attribute characteristics into the combined decision tree model, so as to predict the query purpose of the user, realize intelligent error correction, provide more accurate personnel query, and simultaneously combine the machine learning function of the decision tree model to continuously perform model tuning, reduce manual rule intervention, provide general and convenient basic service, and improve the use experience of the system. Furthermore, in the preferred embodiment, the personal relationship graph and the group relationship graph are combined, so that the relationship network can be automatically adjusted according to the actual working condition of staff, and the defect of the single-dimension relationship graph is avoided.
The present invention will be described in detail with reference to specific scenarios.
The system firstly completes the query condition assembly by utilizing word recognition according to the entry to be queried input by the user. And classifying each word input by the user through a random forest algorithm to obtain the most probable combination condition. And (3) completing the retrieval conforming to the personnel information in the group through the conditions to form a result set, then screening the information based on the authority set, then completing the sequencing of the retrieval results, calling the association relation in the relation map to calculate the result weight, completing the arrangement according to the weight, placing the result with the most compact relation and most possibly associated on the top, and completing the final result output.
In the generation of the personal relationship map and the group relationship map, the system will collect the cases of the final click result of the user, including the click sequence, the number of times of page turning, the page stay time, and input the log to the log analysis means 9. Collecting click conditions of final results, including result residence time, page turning times, click sequence numbers and the like, and adjusting a decision tree result set according to the collected results according to the existing forward records (valve-set clicking) and reverse records (super-valve-set clicking and non-clicking) so as to be used for random forest training; the rule extraction device adjusts the relation model according to the click probability and page turning frequency of the user, and dynamically corrects the weight duty ratio of the user and the current user according to the group to which the user belongs.
The system splits the search term, analyzes the search term, and comprises character type, length, sequence and other attributes. And then identifying the search term. The word recognition algorithm adopts a random forest algorithm, and performs recognition according to the attribute of the search word. And combining the identified search terms to finish the search condition precision.
Specifically, assuming that there are 3 CART trees (type, length, order) in the forest, the total feature number n=3, and each CART tree is set to correspond to a different feature, and the analysis results are shown in table 1:
TABLE 1 CART Tree analysis results Table
CART1: word type
CART2: length of
CART3: sequential order
For example: the user entered "Su Da department of human resources", and the analysis results are shown in table 2 below:
TABLE 2- "Su Da Strong force resource portion" prediction result table
Determination of "Su Dajiang
Determination of "human resources department
According to the decision table, the "Su Dajiang human resources department" detachable conditions are:
name= 'Su Dajiang' and Dept= 'part of human resources'
Or
Name= 'Su Dajiang' and org= 'part of human resources'
After the above condition splitting is completed, it can be obtained that the user intends to search for "user named Su Da strong under the agency of human resources" or "user named Su Da strong under the agency of human resources".
The result screening is completed by combining privacy strategies in enterprises, for example, the privacy of a manager at a higher layer is protected from random harassment, the personal family contact of staff is protected from leakage and the like. The condition information of the staff in the enterprise for privacy protection comprises posts, institutions, departments, job positions and the like. As shown in fig. 6: the left set is the visible information set of the current user, the right set is the search result set, and the intersecting part of the two sets is the reserved item after result screening.
Assuming that a user A, a search result set M of keywords is provided, and assuming that the search result has a default ranking number, the calculation rule of the ranking number M of any element in M is as follows:
m＝a×i+b×j
wherein a is a personal relationship graph weight, and b is a group relationship graph weight; i is personal relationship graph rank number, and b is group relationship graph rank number. For example: user a is a basic manager credit officer group, and for his search results M, the ranking strategy is: { M } × (personal relationship profile×0.7+group relationship profile×0.3). When the user a is a decision maker group of the headquarter manager, his ranking strategy may be adjusted as follows: { M } × (personal relationship profile×0.2+group relationship profile×0.8). Through the model, the requirement that the single relationship map cannot reflect the group communication relationship change after the individual attribute of the user is changed can be well solved.
It can be understood that the scene provided by the invention can analyze the input field information of the address book, including the signs of names, places, posts, organizations, working contents and the like, predict the query purpose of users, realize intelligent error correction and provide more accurate personnel query. And the relationship network is automatically adjusted according to the actual working condition of staff, so that the defect of a single-dimension relationship graph is avoided. Simultaneously has the following advantages:
1. And identifying the search intention to fulfill the aim of accurate search.
2. The result ordering is carried out through the two dimensions of the personal relationship and the group relationship, so that the problem of the scene that the retrieval result set relationship network fails due to the attribute change of the personnel is effectively solved.
3. Model tuning is continuously performed through machine learning, manual rule intervention is reduced, universal and convenient basic service is provided, and the use experience of the system is improved.
Based on the same inventive concept, another aspect of the present invention provides an address book searching apparatus, the address book including a plurality of content classifications, as shown in fig. 5, the address book searching apparatus comprising:
the word segmentation splitting module 1 splits the entry to be checked input by a user to obtain a plurality of segmented words; each of the tokens belongs to one of the content categories, and each of the tokens contains a multi-dimensional attribute feature; each dimension of the attribute feature includes a plurality of different feature contents;
the word segmentation input module 2 inputs each word segmentation into a plurality of decision tree models to obtain the corresponding relation of the characteristic content, the content classification and the probability under each attribute characteristic;
a search combination generation module 3 for determining the content classification to which each word belongs based on each corresponding relation, and generating a search combination;
And the searching module 4 is used for searching in the address book based on the searching combination.
In a preferred embodiment, the content classification comprises: name, organization name, post name, phone number.
In a preferred embodiment, the attribute features include:
character length, word type and the sequence of the word to be checked in the entry where the word is located.
In a preferred embodiment, further comprising:
the model building module is used for building a plurality of initial decision tree models;
and the model training module is used for training each initial decision tree model by utilizing the query vocabulary entries of the marked word segmentation content classification to obtain the plurality of decision tree models.
In a preferred embodiment, the search combination generation module includes:
the average probability generating unit generates average probability of all characteristic contents under each content category according to each corresponding relation;
and the content classification selection unit selects the content classification with the maximum corresponding average probability as the content classification corresponding to the word segmentation.
In a preferred embodiment, as shown in fig. 6, the retrieving module 4 includes:
a person information search unit 41 that searches for a plurality of person information items conforming to the search combination definition content classification, based on the search combination;
A sequence number determining unit 42 for determining a first sequence number in a personal relationship graph corresponding to the user and a second sequence number in a group relationship graph according to the identity of the user inputting the entry to be checked;
an arrangement sequence number generating unit 43 that generates an arrangement sequence number of each piece of personal information with respect to the user, based on the first sequence number and the second sequence number, and the personal relationship map weight and the group relationship map weight corresponding to the user;
and the ordering and displaying unit 44 sequentially displays the personnel information to be displayed according to the generated ordering serial numbers.
In a preferred embodiment, as shown in fig. 7, the retrieving module 4 further comprises:
a right determining unit 45 for determining the viewing right of the user according to the identity of the user inputting the entry to be checked;
a screening unit 46 for determining a portion of the person information which is not to be displayed according to the viewing authority;
correspondingly, the sequencing display unit displays the personnel information in the user viewing authority when sequentially displaying.
In a preferred embodiment, the arrangement sequence number generating unit calculates the arrangement sequence number of the user according to a calculation formula; wherein, the calculation formula is:
m＝a×i+b×j
Wherein a is a personal relationship graph weight, and b is a group relationship graph weight; i is personal relationship graph ranking number, b is group relationship graph ranking number, and m is ranking number.
Based on the same inventive concept, it can be appreciated that the address book retrieval device provided by one aspect of the invention obtains the multidimensional attribute characteristics of each word segment by splitting the to-be-checked entry, and then inputs the multidimensional attribute characteristics into the combined decision tree model, so that the decision tree model predicts the query purpose of a user, intelligent error correction is realized, more accurate personnel query is provided, meanwhile, model tuning is continuously performed by combining the machine learning function of the decision tree model, manual rule intervention is reduced, universal and convenient basic service is provided, and the use experience of a system is improved. Furthermore, in the preferred embodiment, the personal relationship graph and the group relationship graph are combined, so that the relationship network can be automatically adjusted according to the actual working condition of staff, and the defect of the single-dimension relationship graph is avoided.
In view of the hardware level, in order to provide an embodiment of an electronic device for implementing all or part of the content in the address book searching method, the electronic device specifically includes the following contents:
A processor (processor), a memory (memory), a communication interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete communication with each other through the bus; the communication interface is used for realizing information transmission among the server, the device, the distributed message middleware cluster device, various databases, user terminals and other related equipment; the electronic device may be a desktop computer, a tablet computer, a mobile terminal, etc., and the embodiment is not limited thereto. In this embodiment, the electronic device may refer to an embodiment of the address book searching method in the embodiment and an embodiment of the address book searching device, and the contents thereof are incorporated herein, and the repetition is omitted.
Fig. 10 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present invention. As shown in fig. 10, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 10 is exemplary; other types of structures may also be used in addition to or in place of the structures to implement telecommunications functions or other functions.
In one embodiment, the address book retrieval function may be integrated into the CPU 9100. For example, the central processor 9100 may be configured to control as follows:
s1: splitting the entry to be checked input by the user to obtain a plurality of word segments; each of the tokens belongs to one of the content categories, and each of the tokens contains a multi-dimensional attribute feature; each dimension of the attribute feature includes a plurality of different feature contents.
S2: and inputting each word into a plurality of decision tree models to obtain the corresponding relation of the characteristic content, the content classification and the probability under each attribute characteristic.
S3: and determining the content classification to which each word belongs based on each corresponding relation, and generating a retrieval combination.
S4: and searching in the address book based on the searching combination.
From the above description, it can be seen that the electronic device provided by the embodiment of the invention obtains the multidimensional attribute characteristics of each word segment by splitting the entry to be checked, and then inputs the multidimensional attribute characteristics into the combined decision tree model, so that the decision tree model predicts the query purpose of the user, intelligent error correction is realized, more accurate personnel query is provided, meanwhile, model tuning is continuously performed by combining the machine learning function of the decision tree model, manual rule intervention is reduced, universal and convenient basic service is provided, and the use experience of the system is improved.
In another embodiment, the address book searching device may be configured separately from the cpu 9100, for example, the address book searching device may be configured as a chip connected to the cpu 9100, and the address book searching function is implemented under the control of the cpu.
As shown in fig. 10, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 need not include all of the components shown in fig. 10; in addition, the electronic device 9600 may further include components not shown in fig. 10, and reference may be made to the related art.
As shown in fig. 10, the central processor 9100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, which central processor 9100 receives inputs and controls the operation of the various components of the electronic device 9600.
The memory 9140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information about failure may be stored, and a program for executing the information may be stored. And the central processor 9100 can execute the program stored in the memory 9140 to realize information storage or processing, and the like.
The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, but not limited to, an LCD display.
The memory 9140 may be a solid state memory such as Read Only Memory (ROM), random Access Memory (RAM), SIM card, etc. But also a memory which holds information even when powered down, can be selectively erased and provided with further data, an example of which is sometimes referred to as EPROM or the like. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 storing application programs and function programs or a flow for executing operations of the electronic device 9600 by the central processor 9100.
The memory 9140 may also include a data store 9143, the data store 9143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, address book applications, etc.).
The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. A communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, as in the case of conventional mobile communication terminals.
Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, etc., may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and to receive audio input from the microphone 9132 to implement usual telecommunications functions. The audio processor 9130 can include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100 so that sound can be recorded locally through the microphone 9132 and sound stored locally can be played through the speaker 9131.
The embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the address book searching method of the server by the execution subject in the above embodiment, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements all the steps in the address book searching method in the above embodiment.
As can be seen from the above description, the computer readable storage medium provided by the embodiment of the present invention obtains the multidimensional attribute characteristics of each word segment by splitting the entry to be checked, and then inputs the multidimensional attribute characteristics into the combined decision tree model, so as to predict the query purpose of the user, implement intelligent error correction, provide more accurate personnel query, and simultaneously combine the machine learning function of the decision tree model to continuously perform model tuning, reduce manual rule intervention, provide universal and convenient basic service, and improve the use experience of the system.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principles and embodiments of the present invention have been described in detail with reference to specific examples, which are provided to facilitate understanding of the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (12)
1. An address book searching method, wherein the address book comprises a plurality of content classifications, and the content classifications comprise: the address book searching method comprises the following steps of:
splitting the entry to be checked input by the user to obtain a plurality of word segments; each of the tokens belongs to one of the content categories, and each of the tokens contains a multi-dimensional attribute feature comprising: character length, word type and sequence of the word to be checked in the entry where the word is located; each dimension of the attribute feature includes a plurality of different feature contents;
inputting each word segment into a plurality of decision tree models to obtain the corresponding relation of the characteristic content, the content classification and the probability under each attribute characteristic;
determining the content classification of each word segmentation based on each corresponding relation, and generating a retrieval combination;
searching in the address book based on the searching combination;
the searching in the address book based on the searching combination comprises the following steps:
searching a plurality of personnel information meeting the content classification limited by the search combination according to the search combination;
according to the user identity of the entry to be checked, determining a first serial number of each piece of personnel information in a personal relationship graph corresponding to the user and a second serial number in a group relationship graph;
Generating an arrangement sequence number of each piece of personnel information relative to the user according to the first sequence number, the second sequence number, the personal relationship graph weight and the group relationship graph weight corresponding to the user;
and sequentially displaying the personnel information to be displayed according to the generated arrangement serial numbers.
2. The address book retrieval method according to claim 1, further comprising:
establishing a plurality of initial decision tree models;
and training each initial decision tree model by using the query terms of the marked word segmentation content classification to obtain a plurality of decision tree models.
3. The address book retrieval method according to claim 1, wherein the determining the content classification to which each word segment belongs based on each of the correspondence relations includes:
generating average probability of all characteristic contents under each content category according to each corresponding relation;
and selecting the content classification with the maximum corresponding average probability as the content classification corresponding to the word segmentation.
4. The address book retrieval method according to claim 1, wherein the retrieval is performed in the address book based on the retrieval combination, further comprising:
determining the viewing authority of the user according to the user identity of the entry to be checked;
Determining a part which is not displayed in the personnel information according to the viewing authority;
correspondingly, the personnel information in the user viewing authority is displayed when the sequential display is carried out.
5. The address book retrieval method of claim 1, wherein the generating an arrangement number of each piece of personal information with respect to the user includes:
calculating the arrangement sequence number of the user according to a calculation formula; wherein, the calculation formula is:
m＝a×i+b×j
wherein a is a personal relationship graph weight, and b is a group relationship graph weight; i is personal relationship graph ranking number, b is group relationship graph ranking number, and m is ranking number.
6. An address book retrieving apparatus, the address book including a plurality of content classifications, the content classifications comprising: name, organization name, post name, telephone number, the address book search device includes:
the word segmentation splitting module splits the entry to be checked input by the user to obtain a plurality of segmented words; each of the tokens belongs to one of the content categories, and each of the tokens contains a multi-dimensional attribute feature comprising: character length, word type and sequence of the word to be checked in the entry where the word is located; each dimension of the attribute feature includes a plurality of different feature contents;
The word segmentation input module is used for inputting each word segmentation into a plurality of decision tree models to obtain the corresponding relation of the characteristic content, the content classification and the probability under each attribute characteristic;
the search combination generation module is used for determining the content classification of each word segment based on each corresponding relation to generate a search combination;
the retrieval module is used for retrieving in the address book based on the retrieval combination;
the retrieval module comprises:
a personnel information retrieval unit for retrieving a plurality of personnel information conforming to the content classification defined by the retrieval combination according to the retrieval combination;
a serial number determining unit, configured to determine, according to a user identity input to the entry to be checked, a first serial number of each piece of personal information in a personal relationship graph corresponding to the user and a second serial number of each piece of personal information in a group relationship graph;
an arrangement sequence number generating unit, configured to generate an arrangement sequence number of each piece of personnel information relative to the user according to the first sequence number, the second sequence number, and the personal relationship graph weight and the group relationship graph weight corresponding to the user;
and the ordering display unit is used for sequentially displaying the personnel information to be displayed according to the generated ordering sequence number.
7. The address book retrieval device of claim 6, further comprising:
the model building module is used for building a plurality of initial decision tree models;
and the model training module is used for training each initial decision tree model by utilizing the query vocabulary entries of the marked word segmentation content classification to obtain the plurality of decision tree models.
8. The address book retrieval device of claim 6, wherein the retrieval combination generation module comprises:
the average probability generating unit generates average probability of all characteristic contents under each content category according to each corresponding relation;
and the content classification selection unit selects the content classification with the maximum corresponding average probability as the content classification corresponding to the word segmentation.
9. The address book retrieval device of claim 6, wherein the retrieval module further comprises:
the permission determining unit is used for determining the viewing permission of the user according to the user identity of the entry to be checked;
the screening unit is used for determining the part which is not displayed in the personnel information according to the viewing authority;
correspondingly, the sequencing display unit displays the personnel information in the user viewing authority when sequentially displaying.
10. The address book retrieval device according to claim 6, wherein the arrangement number generation unit calculates the arrangement number of the user according to a calculation formula; wherein, the calculation formula is:
m＝a×i+b×j
wherein a is a personal relationship graph weight, and b is a group relationship graph weight; i is personal relationship graph ranking number, b is group relationship graph ranking number, and m is ranking number.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the address book retrieval method of any one of claims 1 to 5 when the program is executed by the processor.
12. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the address book retrieval method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010236187.0A CN111367942B (en) | 2020-03-30 | 2020-03-30 | Address book retrieval method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010236187.0A CN111367942B (en) | 2020-03-30 | 2020-03-30 | Address book retrieval method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111367942A CN111367942A (en) | 2020-07-03 |
| CN111367942B true CN111367942B (en) | 2023-07-21 |
Family
ID=71209319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010236187.0A Active CN111367942B (en) | 2020-03-30 | 2020-03-30 | Address book retrieval method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111367942B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113064918B (en) * | 2021-03-24 | 2024-03-12 | 北京金堤征信服务有限公司 | Enterprise data query method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101894158A (en) * | 2010-07-21 | 2010-11-24 | 同方知网(北京)技术有限公司 | Intelligent retrieval system |
| CN105719661A (en) * | 2016-01-29 | 2016-06-29 | 西安交通大学 | Automatic discrimination method for playing timbre of string instrument |
| CN109117478A (en) * | 2018-07-27 | 2019-01-01 | 北京城市网邻信息技术有限公司 | Recognition methods, device, equipment and the storage medium of contact method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101638821B1 (en) * | 2015-04-16 | 2016-07-12 | 네이버 주식회사 | Method, system and recording medium for providing automatically completed recommended word using domain property |
-
2020
- 2020-03-30 CN CN202010236187.0A patent/CN111367942B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101894158A (en) * | 2010-07-21 | 2010-11-24 | 同方知网(北京)技术有限公司 | Intelligent retrieval system |
| CN105719661A (en) * | 2016-01-29 | 2016-06-29 | 西安交通大学 | Automatic discrimination method for playing timbre of string instrument |
| CN109117478A (en) * | 2018-07-27 | 2019-01-01 | 北京城市网邻信息技术有限公司 | Recognition methods, device, equipment and the storage medium of contact method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111367942A (en) | 2020-07-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11397772B2 (en) | Information search method, apparatus, and system | |
| CN103077050B (en) | A kind of show the method for application information, device and equipment | |
| US20230334089A1 (en) | Entity recognition from an image | |
| US20110145234A1 (en) | Search method and system | |
| US9009132B2 (en) | Location-aware business data retrieval | |
| CN109033156B (en) | Information processing method and device and terminal | |
| US11544307B2 (en) | Personnel selecting device, personnel selecting system, personnel selecting method, and recording medium | |
| CN110516057B (en) | Petition question answering method and device | |
| CN108241690A (en) | A kind of data processing method and device, a kind of device for data processing | |
| CN112417121A (en) | Client intention recognition method and device, computer equipment and storage medium | |
| CN112231452A (en) | Question-answering method, device, equipment and storage medium based on natural language processing | |
| US20140229468A1 (en) | Location-Based Mobile Search | |
| CN110675179A (en) | Marketing information processing method and device, electronic equipment and readable storage medium | |
| CN111367942B (en) | Address book retrieval method and device | |
| CN111160699A (en) | Expert recommendation method and system | |
| CN112597292B (en) | Question reply recommendation method, device, computer equipment and storage medium | |
| CN108595141A (en) | Pronunciation inputting method and device, computer installation and computer readable storage medium | |
| US20210357682A1 (en) | Artificial intelligence driven image retrieval | |
| CN109284423A (en) | Business option card lookup method and device | |
| CN111752898B (en) | File processing method and device | |
| CN110362686B (en) | Word stock generation method and device, terminal equipment and server | |
| CN111507588A (en) | Intelligent recommendation system for intellectual property service | |
| CN110288467B (en) | Data mining method and device, electronic equipment and storage medium | |
| CN113609833A (en) | Dynamic generation method and device of file, computer equipment and storage medium | |
| CN111597453A (en) | User image drawing method and device, computer equipment and computer readable storage 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 |