CN107247792B - Method and device for matching functional departments and computer equipment - Google Patents
Method and device for matching functional departments and computer equipment Download PDFInfo
- Publication number
- CN107247792B CN107247792B CN201710458474.4A CN201710458474A CN107247792B CN 107247792 B CN107247792 B CN 107247792B CN 201710458474 A CN201710458474 A CN 201710458474A CN 107247792 B CN107247792 B CN 107247792B
- Authority
- CN
- China
- Prior art keywords
- place name
- place
- report
- preset
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—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
- G06F16/2462—Approximate or statistical 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
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Remote Sensing (AREA)
- Development Economics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a method, a device and computer equipment for matching functional departments, wherein the method comprises the following steps: acquiring the report text information to obtain place name information corresponding to the report text information; searching a place name matched with the place name information in a preset place name database according to a preset semantic similarity algorithm; and searching corresponding functional departments in a preset mapping database according to the matched place names and the pre-input entry types. The method automatically determines the place name information in the whole process, automatically matches the place name, automatically searches the functional department, does not need manual participation, saves a large amount of labor cost, can quickly obtain feedback of the report content by citizens, improves the municipal service efficiency, and is beneficial to municipal construction.
Description
Technical Field
The invention relates to the field of communication, in particular to a method and a device for matching functional departments and computer equipment.
Background
When the existing citizens report to the municipal department to acquire the information corresponding to the functional department which the citizens want to know, the citizens need to manually put through incoming calls, manually analyze the report content and distribute the report content to the related functional departments in the corresponding areas. For example, when a user reflects a problem of dumping garbage anywhere to a municipal department, the problem needs to be manually analyzed and found to a corresponding intelligent department. Whole process all needs artifical the participation, and the cost of labor is higher, and municipal administration efficiency is lower, is unfavorable for municipal construction.
Disclosure of Invention
The invention provides a method, a device and computer equipment for matching functional departments, which are used for solving the following problems in the prior art: when the existing municipal service system works, the whole process needs manual participation, the labor cost is high, the municipal service efficiency is low, and the municipal construction is not facilitated.
In order to solve the above technical problem, in one aspect, the present invention provides a method for matching functional departments, comprising: acquiring the report text information to obtain place name information corresponding to the report text information; searching a place name matched with the place name information in a preset place name database according to a preset semantic similarity algorithm;
and searching corresponding functional departments in a preset mapping database according to the matched place names and the pre-input entry types.
Optionally, the searching for the place name matched with the place name information in a preset place name database according to a preset semantic similarity algorithm includes: and respectively calculating the semantic similarity between the place name information and each standard place name in the preset place name database, and taking the standard place name which is larger than a preset similarity threshold and corresponds to the maximum semantic similarity as the place name matched with the place name information.
Optionally, before searching for the corresponding functional department in the preset mapping database according to the matched place name and the pre-input entry category, the method further includes: training a preset report type training sample set by adopting a classification algorithm to obtain a report type classifier, wherein the training sample set comprises a plurality of report type samples; acquiring report type related text information in the report text information; and inputting the text information related to the report types into the report type classifier to obtain the pre-input report types.
Optionally, the classification algorithm includes one or more of the following: naive Bayes NB classification algorithm, support vector machine SVM classification algorithm, K nearest KNN classification algorithm and random forest classification algorithm.
Optionally, the report text information includes: and the corresponding text information is obtained after the voice data of the incoming call is converted during the case report, or the text information is sent during the case report.
Optionally, acquiring the report text information to obtain the place name information corresponding to the report text information, including: performing word segmentation processing on the report text information according to a preset word segmentation method to obtain word segmentation results; performing place name part-of-speech tagging on the word segmentation result to obtain a place name word set;
carrying out named entity recognition on the place name word set to obtain a place name entity; and taking the place name word corresponding to the place name entity as the place name information of the place name entity.
Optionally, the predetermined word segmentation method at least includes one of: dictionary two-way maximum matching method, HMM method and CRF method.
Optionally, searching for the place name matched with the place name information in a preset place name database according to a preset semantic similarity algorithm, including: s11, acquiring the place name with the lowest level in the place name information; and S12, the preset place name database comprises standard place names, and the standard place names matched with the obtained place name information are searched in the preset place name database according to the place names according to a preset semantic similarity algorithm, wherein the standard place names are place names named by the standard place names with the lowest level.
Optionally, after S12, the method further includes: s13, under the condition that the matched place name is not searched, the place name word of the last level of the place name is obtained, and the S12 process is executed according to the obtained place name until the matched standard place name is searched.
Optionally, the step of S12, searching a preset place name database for a standard place name matching the obtained place name information according to the place name by a preset semantic similarity algorithm, includes: and respectively calculating the semantic similarity between the place name and each standard place name in the preset place name database, and taking the standard place name which is larger than a preset similarity threshold and corresponds to the maximum semantic similarity as the place name matched with the place name information.
Optionally, S11 includes: arranging the place name words of the place name information according to the input sequence of the entry text information to obtain a place name word list; if the place nouns are English, acquiring a first place noun in the place noun list as a lowest-level place noun; if the place nouns are Chinese, acquiring the last place noun in the place noun list as the place noun with the lowest level;
the obtaining of the place name of the last level of the place name comprises: if the place name is English, acquiring a next place name of the current place name in the place name list; and if the place noun is Chinese, acquiring the last place noun of the current place noun in the place noun list.
Optionally, after searching the corresponding functional department in the preset mapping database according to the matched place name and the pre-input entry category, the method further includes one or more of the following steps: feeding back the telephone of the functional department to the user terminal corresponding to the report text message; calling the functional department for the user terminal corresponding to the report text information; and sending the report information to a terminal of the functional department.
In another aspect, the present invention further provides a device for matching functional departments, comprising: the processing module is used for acquiring the report text information and obtaining the place name information corresponding to the report text information;
the matching module is used for searching a place name matched with the place name information in a preset place name database according to a preset semantic similarity algorithm; and the searching module is used for searching the corresponding functional department in a preset mapping database according to the matched place name and the pre-input entry category.
Optionally, the matching module is specifically configured to: and respectively calculating the semantic similarity between the place name information and each standard place name in the preset place name database, and taking the standard place name which is larger than a preset similarity threshold and corresponds to the maximum semantic similarity as the place name matched with the place name information.
Optionally, the method further includes: the training module is used for training a preset report class training sample set by adopting a classification algorithm to obtain a report class classifier, wherein the training sample set comprises a plurality of report class samples; acquiring report type related text information in the report text information; and inputting the text information related to the report types into the report type classifier to obtain the pre-input report types.
Optionally, the classification algorithm includes one or more of the following: naive Bayes NB classification algorithm, support vector machine SVM classification algorithm, K nearest KNN classification algorithm and random forest classification algorithm.
Optionally, the report text information includes: and the corresponding text information is obtained after the voice data of the incoming call is converted during the case report, or the text information is sent during the case report.
Optionally, the processing module includes: the word segmentation unit is used for carrying out word segmentation processing on the report text information according to a preset word segmentation method to obtain a word segmentation result; the part-of-speech tagging unit is used for performing place name part-of-speech tagging on the word segmentation result to obtain a place name word set; the entity identification unit is used for carrying out named entity identification on the place name word set to obtain a place name entity; and taking the place name word corresponding to the place name entity as the place name information of the place name entity.
Optionally, the predetermined word segmentation method at least includes one of: dictionary two-way maximum matching method, HMM method and CRF method.
Optionally, the matching module includes: a lowest-level place name acquisition unit configured to acquire a lowest-level place name in the place name information; and the standard place name acquisition unit is used for searching the standard place name matched with the acquired place name information in a preset place name database according to the place name by a preset semantic similarity algorithm, wherein the standard place name is the place name named by the lowest-level standard place name.
Optionally, the matching module further includes a last-level place name obtaining unit, configured to execute, after the standard place name obtained by the standard place name obtaining unit is matched with the place name information: and under the condition that the matched place name is not searched, acquiring a place name word of the last level of the place name word, and inputting the acquired place name word into a standard place name acquisition unit until the matched standard place name is searched.
Optionally, when the standard place name obtaining unit is executed, searching a preset place name database for a standard place name matching the obtained place name information according to the place name by a preset semantic similarity algorithm, where the method includes: and respectively calculating the semantic similarity between the place name and each standard place name in the preset place name database, and taking the standard place name which is larger than a preset similarity threshold and corresponds to the maximum semantic similarity as the place name matched with the place name information.
Optionally, the lowest-level place name obtaining unit includes: the sequence arrangement subunit is used for arranging the place names of the place name information according to the input sequence of the report text information to obtain a place name list; a place name recognition subunit, configured to, if the place name is english, obtain a first place name in the place name list as a lowest-level place name; if the place nouns are Chinese, acquiring the last place noun in the place noun list as the place noun with the lowest level;
the upper-level place name obtaining unit comprises: a language level place name recognition subunit, configured to, if the place name is english, obtain a next place name of the current place name in the place name list; if the place noun is Chinese, acquiring a last place noun of a current place noun in the place noun list; and the circular matching subunit is used for inputting the acquired place name words into the standard place name acquisition unit until the matched standard place names are searched.
Optionally, the method further includes: and the execution module is used for feeding back the telephone of the functional department to the user terminal corresponding to the report text information, calling the functional department for the user terminal, and/or sending the report information to the terminal of the functional department.
In another aspect, the present invention further provides a computer storage medium storing a computer program, which when executed by a processor implements the steps of a method for matching functional departments as described above.
In another aspect, the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for matching functional departments.
The invention has the following beneficial effects:
the invention obtains the report text information of the municipal service system to obtain the place name information corresponding to the report text information, searches the place name matched with the place name information in the preset place name database according to the preset semantic similarity algorithm, and searches the function department corresponding to the report text information by combining the pre-input report categories, the whole process automatically determines the place name information, automatically matches the place name, automatically searches the function department without manual participation, saves a large amount of labor cost, particularly for municipal service, citizens can quickly obtain the feedback of the report content, improves the municipal service efficiency, is beneficial to municipal construction, and solves the following problems in the prior art: when the existing service system works, the whole process needs manual participation, the labor cost is high, especially for municipal service, the municipal service efficiency is low, and the municipal construction is not facilitated
Drawings
FIG. 1 is a flow chart of a method of matching functional departments in a first embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an apparatus for matching functional departments according to a second embodiment of the present invention;
FIG. 3 is a flow chart of the computer device matching functional division in a third embodiment of the present invention.
Detailed Description
In order to solve the following problems in the prior art: when the existing municipal service system works, the whole process needs manual work, the labor cost is high, the municipal service efficiency is low, and the municipal construction is not facilitated; the invention provides a method, a device and computer equipment for matching functional departments, which are further described in detail in the following with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
The first embodiment of the present invention provides a method for matching functional departments, the flow of the method is shown in fig. 1, and the method includes steps S102 to S106:
s102, acquiring the report text information to obtain place name information corresponding to the report text information;
s104, searching a place name matched with the place name information in a preset place name database according to a preset semantic similarity algorithm;
and S106, searching corresponding functional departments in a preset mapping database according to the matched place names and the pre-input entry types.
The acquired report text information can be report text information of a municipal service system to obtain place name information corresponding to the report text information, a preset place name database is searched for a place name matched with the place name information according to a preset semantic similarity algorithm, and a function department corresponding to the report text information is searched for by combining with a pre-input report category, the place name information is automatically determined in the whole process, the place name is automatically matched, the function department is automatically searched for, manual participation is not needed, a large amount of labor cost is saved, citizens can quickly acquire feedback of report content, the service efficiency is improved, the municipal construction is facilitated, and the following problems in the prior art are solved: when the existing service system works, the whole process needs manual participation, the labor cost is high, especially for municipal service, the municipal service efficiency is low, and the municipal construction is not facilitated.
In the implementation process, when the place name matched with the place name information is searched in the preset place name database according to the preset semantic similarity algorithm, the semantic similarity between the place name information and each standard place name in the preset place name database can be respectively calculated, and the standard place name which is larger than the preset similarity threshold and corresponds to the maximum semantic similarity is used as the place name matched with the place name information. The standard place name is a place name named by the lowest-level standard place name or a complete place name, and when the standard place name is the complete place name, similarity calculation can be performed between the complete place name information and the standard place name.
Before searching corresponding functional departments in a preset mapping database according to the matched place names and the pre-input report types, training a preset report type training sample set by adopting a classification algorithm to obtain a report type classifier, wherein the training sample set comprises a plurality of report type samples; acquiring report type related text information in the report text information; and inputting the text information related to the report types into a report type classifier to obtain the pre-input report types. The classification algorithm comprises one or more of the following steps: naive Bayes NB classification algorithm, support vector machine SVM classification algorithm, K nearest KNN classification algorithm and random forest classification algorithm.
Through the process, the input report types can be quickly acquired so as to be convenient for matching of functional departments.
Because users using the service system to report are different, the reporting modes are different; some people may call the report by telephone, for example, when an alarm is needed when a fighting event occurs, a citizen user may choose to call the municipal service system by calling the telephone; some users may report by sending information, for example, when a citizen wants to respond to a garbage disposal problem in a certain area and wants to know where the problem is responsible, the problem is not to be solved urgently, and therefore, the citizen may report by sending a short message to a service system. Therefore, when acquiring the report text message, the report text message in the embodiment of the present invention may include a text message corresponding to the converted voice data of the incoming call during reporting, or a text message sent during reporting. Therefore, no matter which way the user reports, the corresponding report text information can be acquired, and the system processing performance is enhanced.
In this embodiment, by acquiring the application text information, the place name information corresponding to the application text information can be further obtained, and during specific processing, the following process is included:
performing word segmentation processing on the report text information according to a preset word segmentation method to obtain a word segmentation result, and performing place name and part of speech tagging on the word segmentation result to obtain a place name and part of speech set, wherein the place name and part of speech are ns, for example; in the process, word segmentation is carried out together with part-of-speech tagging, wherein the part-of-speech tagging is used for tagging the part-of-speech of each word marked in a word segmentation dictionary into a word segmentation result. The predetermined word segmentation method may be various, for example, a dictionary two-way maximum matching method, an HMM method, or a CRF method.
And then, carrying out named entity recognition on the place name word set to obtain a place name entity, and taking the place name word corresponding to the place name entity as the place name information of the place name entity. In practice, the place name information may include one or more compound place names, and when a plurality of compound place names are included, for example, the place name information includes three place names but refers to one place name, and thus needs to be obtained through entity recognition, and the place name entity obtained through entity recognition is the place name information including one place name or a plurality of place name word compounds.
Through the process, the place name information related to the report of the citizen user can be obtained from the acquired report text information, and a solid foundation is provided for automatic report.
When searching for a place name matched with place name information in a preset place name database according to a preset semantic similarity algorithm, since the place name information may usually comprise a plurality of place names, the place name information is usually matched with a standard place name in the place name database, wherein the standard place name is the place name named by the standard place name with the lowest level. Therefore, in implementation, it is necessary to determine which local nouns to recognize first according to the language condition of the report text message, and the specific implementation process is as follows:
and S11, acquiring the place name with the lowest level in the place name information.
And S12, the preset place name database comprises standard place names, and the standard place names matched with the obtained place name information are searched in the preset place name database according to the place names according to a preset semantic similarity algorithm, wherein the standard place names are place names named by the standard place names with the lowest level.
And S13, under the condition that the matched place name is not searched, acquiring the place name word of the last level of the place name word, and executing the S12 process according to the acquired place name word until the matched standard place name is searched.
Specifically, the semantic similarity between the geographical term in S12 and each standard geographical name in the preset geographical name database is calculated, and the standard geographical name corresponding to the maximum semantic similarity greater than the preset similarity threshold is used as the geographical name matched with the geographical name information.
S11 specifically includes: arranging place names of the place name information according to the input sequence of the report text information to obtain a place name list; if the place nouns are English, acquiring a first place noun in the place noun list as a lowest-level place noun; if the place nouns are Chinese, acquiring the last place noun in the place noun list as the place noun with the lowest level; in S13, acquiring the place name of the last level of the place name includes: if the place noun is English, acquiring a next place noun of the current place noun in the place noun list; if the local noun is Chinese, the last local noun of the current local noun in the local noun list is obtained.
For example, when the place name information is the third university of the kakkaiwa in beijing, the place name information corresponds to a plurality of place names in sequence of "beijing, kakkaiwa, and the third primary school of kakkaiwa", when matching is performed, the place name matching is performed starting from the place name word of "the third university of kakkaiwa", and if the place name word of "the third university of kakkaiwa" does not match the place name, the matching is performed using "the kakkaiwa".
When the place name information is 'Baihua Silu, Futian District, Shenzhen City, Guingdong Provincy', the place name words corresponding to the place name information are 'Baihua Silu, Futian District, Shenzhen City, Guingdong Provincy' in sequence, when matching is carried out, the place name matching is carried out from the place name word 'Baihua Silu', if the place name word 'Baihua Silu' does not match the place name, the 'Futian District' is used for matching, and if the 'Futian District' does not match the place name, the 'Shenzhen City' is used for matching.
Because the Chinese and English are different in the expression modes of the place name information, namely the Chinese habit broadcasts or records the place name information according to the sequence from large to small, such as province, city and county, and the English habit broadcasts or records the place name information according to the sequence from small to large, such as county, city, province and the like, the embodiment needs to execute different matching modes according to different case-reporting languages, so that the embodiment can be flexibly suitable for the types of the case-reporting languages and enhance the performance of the case-reporting system.
After the corresponding place name is matched, the corresponding functional department can be searched in a preset mapping database by combining the entry types input by the entry user in advance. For the preset mapping database, it stores the relevant information of each functional department in each region of the city, such as the functional department, the location, the responsibility, etc.
After searching the corresponding functional department in the preset mapping database according to the matched place name and the pre-input report category, the method further comprises the following step or steps: the telephone of the functional department can be fed back to the user terminal corresponding to the report text information; calling a functional department for the user terminal; and sending the report information to a terminal of the functional department. If the citizen user reports the case by calling in the service system, the telephone of the corresponding functional department can be directly broadcasted in the telephone by voice, and the telephone can be directly forwarded to call in the functional department corresponding to the telephone; if the user reports by sending information to the service system, the telephone of the corresponding functional department can be sent to the reporting user terminal by information.
A second embodiment of the present invention provides an apparatus for matching functional departments, which is schematically shown in fig. 2 and includes:
the processing module 10 is configured to obtain the report text information, and obtain place name information corresponding to the report text information; the matching module 11 is coupled with the processing module 10 and used for searching the place names matched with the place name information in the preset place name database according to a preset semantic similarity algorithm; and the searching module 12 is coupled with the matching module 11 and is used for searching the corresponding functional department in the preset mapping database according to the matched place name and the pre-input entry category.
In the whole process of the embodiment of the invention, the place name information is automatically determined, the place name is automatically matched, the functional department is automatically searched, manual participation is not needed, a large amount of labor cost is saved, citizens can quickly obtain feedback of the report content, the service efficiency is improved, the municipal construction is facilitated, and the following problems in the prior art are solved: when the existing service system works, the whole process needs manual participation, the labor cost is high, especially for municipal service, the municipal service efficiency is low, and the municipal construction is not facilitated.
Because users using the service system to report are different, the reporting modes are different; some people may call the report by telephone, for example, when an alarm is needed when a fighting event occurs, a citizen user may choose to call the municipal service system by calling the telephone; some users may report by sending information, for example, when a citizen wants to respond to a garbage disposal problem in a certain area and wants to know where the problem is responsible, the problem is not to be solved urgently, and therefore, the citizen may report by sending a short message to a service system. Therefore, the reporting text message may be a text message corresponding to the converted voice data of the incoming call at the time of reporting, or a text message sent at the time of reporting. Therefore, no matter which way the user reports, the corresponding report text information can be acquired, and the system processing performance is enhanced.
The matching module 11 is specifically configured to: and respectively calculating the semantic similarity between the place name information and each standard place name in the preset place name database, and taking the standard place name which is larger than a preset similarity threshold and corresponds to the maximum semantic similarity as the place name matched with the place name information. The standard place name is a place name named by the lowest-level standard place name or a complete place name, and when the standard place name is the complete place name, similarity calculation can be performed between the complete place name information and the standard place name.
The device may further include a training module coupled to the search module 12, configured to train a preset report category training sample set by using a classification algorithm to obtain a report category classifier, where the training sample set includes samples of a plurality of report categories; acquiring report type related text information in the report text information; and inputting the text information related to the report types into a report type classifier to obtain the pre-input report types. The classification algorithm comprises one or more of the following steps: naive Bayes NB classification algorithm, support vector machine SVM classification algorithm, K nearest KNN classification algorithm and random forest classification algorithm. Through the process, the input report types can be quickly acquired so as to be convenient for matching of functional departments.
The processing module 10 specifically includes a word segmentation unit, a part-of-speech tagging unit, and an entity identification unit.
The word segmentation unit is used for carrying out word segmentation processing on the report text information according to a preset word segmentation method to obtain a word segmentation result. For example, a part of speech ns is a place name; in the process, word segmentation is carried out together with part-of-speech tagging, wherein the part-of-speech tagging is used for tagging the part-of-speech of each word marked in a word segmentation dictionary into a word segmentation result. The predetermined word segmentation method may be various, for example, a dictionary two-way maximum matching method, an HMM method, or a CRF method.
The part-of-speech tagging unit is used for performing place name part-of-speech tagging on the word segmentation result to obtain a place name word set; and carrying out named entity recognition on the place name word set to obtain a place name entity.
And the entity identification unit is used for taking the place name word corresponding to the place name entity as the place name information of the place name entity.
In practice, the place name information may include one or more compound place names, and when a plurality of compound place names are included, for example, the place name information includes three place names but refers to one place name, and thus needs to be obtained through entity recognition, and the place name entity obtained through entity recognition is the place name information including one place name or a plurality of place name word compounds.
Through the process, the place name information related to the report of the citizen user can be obtained from the acquired report text information, and a solid foundation is provided for automatic report.
To simplify the operation of the noun process of recognition, the matching module 11 may include:
a lowest-level place name acquisition unit for acquiring a lowest-level place name in the place name information;
and the standard place name acquisition unit is used for searching a standard place name matched with the acquired place name information in the preset place name database according to the place name by a preset semantic similarity algorithm, wherein the standard place name is the place name named by the standard place name with the lowest level.
A last-level place name obtaining unit configured to execute, after the standard place name matched with the place name information obtained by the standard place name obtaining unit: and under the condition that the matched place name is not searched, acquiring the place name word of the last level of the place name word, and inputting the acquired place name word into the standard place name acquisition unit until the matched standard place name is searched.
When the standard place name acquisition unit is executed, the searching of the standard place name matched with the acquired place name information in the preset place name database according to the place name by a preset semantic similarity algorithm comprises the following steps: and respectively calculating the semantic similarity between the place name and each standard place name in the preset place name database, and taking the standard place name which is larger than a preset similarity threshold and corresponds to the maximum semantic similarity as the place name matched with the place name information.
And the lowest-level place name acquisition unit comprises a sequential arrangement subunit and a first place name recognition subunit.
The system comprises a sequential arrangement subunit, a search unit and a search unit, wherein the sequential arrangement subunit is used for arranging the place names of the place name information according to the input sequence of the report text information to obtain a place name list; the first place name recognition subunit is used for acquiring a first place name in the place name list as a lowest-level place name if the place name is English; if the place noun is Chinese, the last place noun in the place noun list is obtained as the place noun with the lowest level.
The upper-level place name acquisition unit comprises a language-level place name recognition subunit and a cycle matching subunit. The language level noun identification subunit is used for acquiring the place name words of the last level of the place nouns, and comprises the following steps: if the place noun is English, acquiring a next place noun of the current place noun in the place noun list; if the local noun is Chinese, the last local noun of the current local noun in the local noun list is obtained. And the circular matching subunit is used for inputting the acquired place name words into the standard place name acquisition unit until the matched standard place names are searched.
The embodiment can execute different matching modes according to different report languages, so that the method can be flexibly suitable for the types of the report languages, and the performance of the report system is enhanced.
The above apparatus may further include: and the execution module is coupled with the search module and is used for feeding back the telephone of the functional department to the user terminal corresponding to the report text information, calling the functional department for the user terminal and/or sending the report information to the terminal of the functional department. If the citizen user reports the case by calling in the service system, the telephone of the corresponding functional department can be directly broadcasted in the telephone by voice, and the telephone can be directly forwarded to call in the functional department corresponding to the telephone; if the user reports by sending information to the service system, the telephone of the corresponding functional department can be sent to the reporting user terminal by information.
The third embodiment of the present invention also provides a computer device, which includes a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the method for matching functional departments of the first embodiment. In practice, the computer program may be stored in a computer storage medium.
For example, the processor, when executing the computer program, implements the following process of fig. 3:
and S1, acquiring the report text information. In the process, information such as the problem category or the complaint content can be determined according to the report text information.
S2, performing word segmentation, part of speech tagging, Named Entity Recognition (NER) and place name information extraction on the report text information.
And S3, judging whether the place name database has the place name with the preset matching degree with the place name information. If so, S4 is performed, otherwise S6 is performed.
And S4, searching corresponding functional departments in a preset mapping database according to the articles in the local nouns and the article text information.
And S5, feeding back the searched functional departments to citizen users.
S6, the next place name in the place name information is searched according to the sequence, and the S3 is returned. Wherein, the sequence may be a sequence mode of the place name information or a reverse mode of the place name information.
For example, when a citizen calls in to report that there is a traffic accident near the third primary school of the middle-school village of the sea lake area of Beijing city, the place name information is the third primary school of the middle-school village of the sea lake area of Beijing city, and a plurality of place names corresponding to the place name information are sequentially the third primary schools of the Beijing city, the sea lake area and the middle-school village, and the corresponding report types are traffic and sudden accident types, so that the system can be matched with a traffic police department when searching for an intelligent department, and can provide the citizen with the telephone of a traffic police department near the third primary school of the middle-school village so as to deal with the problem in time.
This system of this embodiment manual can realize the automatic circulation of municipal administration application of notes, improves municipal administration efficiency of service, reduces the cost of labor.
Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes. Optionally, in this embodiment, the processor executes the method steps described in the above embodiments according to the program code stored in the storage medium. Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again. It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
Although the preferred embodiments of the present invention have been disclosed for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, and the scope of the invention should not be limited to the embodiments described above.
Claims (14)
1. A method of matching functional departments for citizens to report to municipal departments, comprising:
acquiring the report text information to obtain place name information corresponding to the report text information; the report text information comprises: text information corresponding to the converted voice data of the incoming call when the case is reported;
searching a place name matched with the place name information in a preset place name database according to a preset semantic similarity algorithm;
searching corresponding functional departments in a preset mapping database according to the matched place names and the pre-input entry types;
the searching for the place name matched with the place name information in a preset place name database according to a preset semantic similarity algorithm comprises the following steps:
s11, acquiring the place name with the lowest level in the place name information;
s12, the preset place name database comprises standard place names, and the standard place names matched with the obtained place name information are searched in the preset place name database according to the place names according to a preset semantic similarity algorithm, wherein the standard place names are place names named by the standard place names with the lowest level;
s13, under the condition that the matched place name is not searched, obtaining the place name word of the last level of the place name word, and executing the S12 process according to the obtained place name until the matched standard place name is searched;
s12, searching a standard place name matched with the acquired place name information in a preset place name database according to the place name by a preset semantic similarity algorithm, wherein the method comprises the following steps:
respectively calculating semantic similarity between the place name and each standard place name in the preset place name database, and taking the standard place name which is larger than a preset similarity threshold and corresponds to the maximum semantic similarity as the place name matched with the place name information;
after searching the corresponding functional department in the preset mapping database according to the matched place name and the pre-input entry category, the method further comprises the following steps:
feeding back the telephone of the functional department to the user terminal corresponding to the report text message; calling the functional department for the user terminal corresponding to the report text information; and sending the report information to a terminal of the functional department.
2. The method of claim 1, wherein before searching the database for the corresponding functional department according to the matched place name and the pre-entered entry category, the method further comprises:
training a preset report type training sample set by adopting a classification algorithm to obtain a report type classifier, wherein the training sample set comprises a plurality of report type samples;
acquiring report type related text information in the report text information;
and inputting the text information related to the report types into the report type classifier to obtain the pre-input report types.
3. The method of claim 2,
the classification algorithm comprises one or more of the following: naive Bayes NB classification algorithm, support vector machine SVM classification algorithm, K nearest KNN classification algorithm and random forest classification algorithm.
4. The method of claim 1, wherein obtaining an entry text message and obtaining location name information corresponding to the entry text message comprises:
performing word segmentation processing on the report text information according to a preset word segmentation method to obtain word segmentation results;
performing place name part-of-speech tagging on the word segmentation result to obtain a place name word set;
carrying out named entity recognition on the place name word set to obtain a place name entity;
and taking the place name word corresponding to the place name entity as the place name information of the place name entity.
5. The method of claim 4, wherein the predetermined word segmentation method comprises at least one of: dictionary two-way maximum matching method, HMM method and CRF method.
6. The method of claim 1, wherein S11 includes:
arranging the place name words of the place name information according to the input sequence of the entry text information to obtain a place name word list;
if the place nouns are English, acquiring a first place noun in the place noun list as a lowest-level place noun; if the place nouns are Chinese, acquiring the last place noun in the place noun list as the place noun with the lowest level;
the obtaining of the place name of the last level of the place name comprises:
if the place name is English, acquiring a next place name of the current place name in the place name list; and if the place noun is Chinese, acquiring the last place noun of the current place noun in the place noun list.
7. A device that matches functional department for citizens report to municipal department, its characterized in that includes:
the processing module is used for acquiring the report text information and obtaining the place name information corresponding to the report text information; the report text information comprises: text information corresponding to the converted voice data of the incoming call when the case is reported;
the matching module is used for searching a place name matched with the place name information in a preset place name database according to a preset semantic similarity algorithm;
the searching module is used for searching corresponding functional departments in a preset mapping database according to the matched place names and the pre-input entry categories;
the execution module is used for feeding back the telephone of the functional department to the user terminal corresponding to the report text information, calling the functional department for the user terminal and sending the report information to the terminal of the functional department;
wherein the matching module comprises:
a lowest-level place name acquisition unit configured to acquire a lowest-level place name in the place name information;
the standard place name acquisition unit is used for searching the standard place name matched with the acquired place name information in a preset place name database according to the place name by a preset semantic similarity algorithm, wherein the standard place name is the place name named by the lowest-level standard place name;
a last-level place name obtaining unit configured to execute, after the standard place name matched with the place name information obtained by the standard place name obtaining unit: under the condition that a matched place name is not searched, a place name word of the last level of the place name word is acquired, and the acquired place name word is input into a standard place name acquisition unit until the matched standard place name is searched;
when the standard place name acquisition unit is executed, searching a standard place name matched with the acquired place name information in a preset place name database according to the place name by a preset semantic similarity algorithm, wherein the standard place name acquisition unit comprises the following steps:
and respectively calculating the semantic similarity between the place name and each standard place name in the preset place name database, and taking the standard place name which is larger than a preset similarity threshold and corresponds to the maximum semantic similarity as the place name matched with the place name information.
8. The apparatus of claim 7, further comprising:
the training module is used for training a preset report class training sample set by adopting a classification algorithm to obtain a report class classifier, wherein the training sample set comprises a plurality of report class samples; acquiring report type related text information in the report text information; and inputting the text information related to the report types into the report type classifier to obtain the pre-input report types.
9. The apparatus of claim 8, wherein the classification algorithm comprises one or more of: naive Bayes NB classification algorithm, support vector machine SVM classification algorithm, K nearest KNN classification algorithm and random forest classification algorithm.
10. The apparatus of claim 7, wherein the processing module comprises:
the word segmentation unit is used for carrying out word segmentation processing on the report text information according to a preset word segmentation method to obtain a word segmentation result;
the part-of-speech tagging unit is used for performing place name part-of-speech tagging on the word segmentation result to obtain a place name word set;
the entity identification unit is used for carrying out named entity identification on the place name word set to obtain a place name entity; and taking the place name word corresponding to the place name entity as the place name information of the place name entity.
11. The apparatus of claim 10, wherein the predetermined word segmentation method comprises at least one of: dictionary two-way maximum matching method, HMM method and CRF method.
12. The apparatus of claim 7, wherein the lowest-level place name acquiring unit comprises:
the sequence arrangement subunit is used for arranging the place names of the place name information according to the input sequence of the report text information to obtain a place name list;
a place name recognition subunit, configured to, if the place name is english, obtain a first place name in the place name list as a lowest-level place name; if the place nouns are Chinese, acquiring the last place noun in the place noun list as the place noun with the lowest level;
the upper-level place name obtaining unit comprises:
a language level place name recognition subunit, configured to, if the place name is english, obtain a next place name of the current place name in the place name list; if the place noun is Chinese, acquiring a last place noun of a current place noun in the place noun list;
and the circular matching subunit is used for inputting the acquired place name words into the standard place name acquisition unit until the matched standard place names are searched.
13. A computer storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of a method of matching functional departments of any one of claims 1 to 6.
14. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of a method of matching functional departments as claimed in any one of claims 1 to 6 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710458474.4A CN107247792B (en) | 2017-06-16 | 2017-06-16 | Method and device for matching functional departments and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710458474.4A CN107247792B (en) | 2017-06-16 | 2017-06-16 | Method and device for matching functional departments and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107247792A CN107247792A (en) | 2017-10-13 |
| CN107247792B true CN107247792B (en) | 2021-01-15 |
Family
ID=60019250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710458474.4A Active CN107247792B (en) | 2017-06-16 | 2017-06-16 | Method and device for matching functional departments and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107247792B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197194A (en) * | 2017-12-27 | 2018-06-22 | 贵州小爱机器人科技有限公司 | A kind of processing method and system of information of reporting a case to the security authorities |
| CN108305050B (en) * | 2018-02-08 | 2023-04-07 | 贵州小爱机器人科技有限公司 | Method, device, equipment and medium for extracting report information and service demand information |
| CN109241240A (en) * | 2018-08-17 | 2019-01-18 | 国家电网有限公司客户服务中心 | Power failure repairing information automatically forwarding method |
| CN111144121B (en) * | 2019-12-27 | 2021-12-03 | 北大方正集团有限公司 | Geographical name recognition method and device, electronic equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440311A (en) * | 2013-08-27 | 2013-12-11 | 深圳市华傲数据技术有限公司 | Method and system for identifying geographical name entities |
| CN104281615A (en) * | 2013-07-08 | 2015-01-14 | 中国移动通信集团甘肃有限公司 | Complaint handling method and system |
| CN104408093A (en) * | 2014-11-14 | 2015-03-11 | 中国科学院计算技术研究所 | News event element extracting method and device |
| CN106326458A (en) * | 2016-06-02 | 2017-01-11 | 广西智度信息科技有限公司 | Method for classifying city management cases based on text classification |
-
2017
- 2017-06-16 CN CN201710458474.4A patent/CN107247792B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104281615A (en) * | 2013-07-08 | 2015-01-14 | 中国移动通信集团甘肃有限公司 | Complaint handling method and system |
| CN103440311A (en) * | 2013-08-27 | 2013-12-11 | 深圳市华傲数据技术有限公司 | Method and system for identifying geographical name entities |
| CN104408093A (en) * | 2014-11-14 | 2015-03-11 | 中国科学院计算技术研究所 | News event element extracting method and device |
| CN106326458A (en) * | 2016-06-02 | 2017-01-11 | 广西智度信息科技有限公司 | Method for classifying city management cases based on text classification |
Non-Patent Citations (1)
| Title |
|---|
| 语义相似性度量技术在地名匹配研究中的应用;王俊超等;《辽宁工程技术大学学报（自然科学版）》;20121231;第871-874页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107247792A (en) | 2017-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145095B (en) | Place name information matching method, information matching device and computer equipment | |
| CN107247792B (en) | Method and device for matching functional departments and computer equipment | |
| CN109670163B (en) | Information identification method, information recommendation method, template construction method and computing device | |
| US20170011117A1 (en) | Help Processing Method and Device Based on Semantic Recognition | |
| CN107577755B (en) | Searching method | |
| JP6355840B2 (en) | Stopword identification method and apparatus | |
| CN108121455B (en) | Identification correction method and device | |
| CN106959976B (en) | Search processing method and device | |
| CN105827787B (en) | number marking method and device | |
| CN113051389B (en) | Knowledge pushing method and device | |
| CN110750626B (en) | Scene-based task-driven multi-turn dialogue method and system | |
| CN113128205B (en) | Scenario information processing method and device, electronic equipment and storage medium | |
| CN112487159B (en) | Search method, search device, and computer-readable storage medium | |
| US11216894B2 (en) | Image-based semantic accommodation search | |
| CN116860957A (en) | Enterprise screening method, device and medium based on large language model | |
| CN111831687A (en) | Data query optimization method and device, computer equipment and storage medium | |
| CN110929014A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN110781279B (en) | Method and device for constructing ASR/NLU engine cross optimization data closed loop | |
| CN114242047A (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN109902099B (en) | Public opinion tracking method and device based on graphic and text big data and computer equipment | |
| US11726972B2 (en) | Directed data indexing based on conceptual relevance | |
| CN112579944A (en) | Page jump processing method and device and electronic equipment | |
| CN112015773A (en) | Knowledge base retrieval method and device, electronic equipment and storage medium | |
| JP2019117568A (en) | Automatic answering device and automatic answering method | |
| CN113536788B (en) | Information processing method, device, storage medium and equipment |
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 |