CN110930990A - Passenger flow volume statistical method, device, equipment and medium based on voice recognition - Google Patents
Passenger flow volume statistical method, device, equipment and medium based on voice recognition Download PDFInfo
- Publication number
- CN110930990A CN110930990A CN201911198405.XA CN201911198405A CN110930990A CN 110930990 A CN110930990 A CN 110930990A CN 201911198405 A CN201911198405 A CN 201911198405A CN 110930990 A CN110930990 A CN 110930990A
- Authority
- CN
- China
- Prior art keywords
- voice
- passenger flow
- target
- time period
- voice 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.)
- Pending
Links
- 238000007619 statistical method Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000004590 computer program Methods 0.000 claims description 13
- 230000015654 memory Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000013486 operation strategy Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011410 subtraction method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/04—Segmentation; Word boundary detection
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a statistical method, a device, equipment and a medium of passenger flow based on voice recognition, wherein the method comprises the following steps: acquiring a voice set of a specified time period; voice information for recording voice sent by employees in the target store is contained in the voice set; searching target voice information containing the reception keywords from the voice set; and determining the passenger flow in the specified time period according to the searched target voice information. According to the embodiment of the application, the voice set of the staff in the target store is obtained, the target voice information is screened from the voice set through the keywords, the passenger flow in the appointed time period is determined, the staff and the clients are distinguished, the situation that the staff is mistaken for the clients is reduced, the passenger flow obtained through statistics does not contain the number of the staff, and the passenger flow statistics accuracy is improved.
Description
Technical Field
The present application relates to the field of people flow statistics, and in particular, to a method, an apparatus, a computer device, and a medium for statistics of passenger flow based on speech recognition.
Background
Under the era of rapid economic development, more and more shops are added on the market, the passenger flow volume in a physical store gets more and more attention, the passenger flow volume reflects the marketing condition of one store, the larger the passenger flow volume is, the better the marketing condition of the store is, and the worse the marketing condition of the store is if the passenger flow volume is smaller.
Generally, the passenger flow volume of an store is counted through an infrared sensor, a camera and the like, but the passenger flow volume of the store cannot be distinguished from the difference between an employee and a client through the method for counting the passenger flow volume of the store, the employee is often taken as the client to count the passenger flow volume, and the passenger flow volume obtained through counting is inaccurate.
Disclosure of Invention
In view of the above, an object of the present application is to provide a method, an apparatus, a computer device and a medium for counting passenger flow based on speech recognition, so as to solve the problem of how to improve the accuracy of passenger flow counting in the prior art.
In a first aspect, an embodiment of the present application provides a method for counting passenger flow based on speech recognition, including:
acquiring a voice set of a specified time period; voice information for recording voice sent by employees in the target store is contained in the voice set;
searching target voice information containing the reception keywords from the voice set;
and determining the passenger flow of the specified time period according to the searched target voice information.
Optionally, the statistical method further includes:
determining the peak time of passenger flow according to the passenger flow volume of each time interval;
and determining the operation strategy of the target store according to the passenger flow peak time.
Optionally, after the step of determining the peak time of the passenger flow, before the step of determining the operation policy of the target store according to the peak time of the passenger flow, the method further includes:
and adjusting the time range of each passenger flow peak period according to the tightness degree of the time distribution of the passenger flow peak period.
Optionally, the operation policy includes any one or two of the following:
determining the scheduling rules of the employees in the target store according to the passenger flow peak time period; or determining the marketing plan of the target store according to the passenger flow peak time.
Optionally, the searching for the target voice information containing the reception keyword from the voice set includes:
converting each voice message in the voice set into a voice text;
and inputting each voice text into the trained keyword recognition model to determine target voice information containing the reception keyword.
Optionally, the obtaining of the voice information is implemented by the following steps:
acquiring voice data of each employee in the target store within the specified time period;
the speech data is divided into at least one speech message using a dialog blank threshold.
Optionally, the processing process of the voice uttered by the employee includes the following steps:
acquiring the voice to be processed corresponding to each employee in the target store within the specified time period;
and aiming at the voice to be processed corresponding to each employee, denoising the voice to be processed so as to screen out the voice corresponding to the employee.
In a second aspect, an embodiment of the present application provides a device for counting passenger flow based on speech recognition, including:
the acquisition module is used for acquiring a voice set of a specified time period; voice information for recording voice sent by employees in the target store is contained in the voice set;
the searching module is used for searching target voice information containing the reception keywords from the voice set;
and the determining module is used for determining the passenger flow in the specified time period according to the searched target voice information.
In a third aspect, an embodiment of the present application provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the steps of the above method when executing the computer program.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, performs the steps of the above method.
The method for counting the passenger flow based on the voice recognition comprises the steps of firstly, acquiring a voice set of a specified time period; voice information for recording voice sent by employees in the target store is contained in the voice set; then, searching target voice information containing the reception keywords from the voice set; and finally, determining the passenger flow in the specified time period according to the searched target voice information.
In the prior art, the passenger flow in the target store is obtained through the infrared sensor and the camera, the difference between a client and an employee cannot be distinguished, the employee is easily taken as the client to carry out statistics, the passenger flow obtained through statistics possibly comprises the number of the employees, and the accuracy of the passenger flow statistics is reduced. In the method, the voice set of the staff in the target store is obtained, the target voice information is screened from the voice set through the keywords, the passenger flow in the specified time period is determined, the staff and the clients are distinguished, the condition that the staff is mistaken for the clients is reduced, the passenger flow obtained through statistics does not contain the number of the staff, and the passenger flow statistics accuracy is improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic basic flow chart of a method for counting passenger flow based on speech recognition according to an embodiment of the present application;
fig. 2 is a schematic basic flowchart of a method for determining an operation policy according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a device for counting passenger flow based on speech recognition according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a computer device 400 according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
In prior art, adopt infrared sensor statistics of the interior passenger flow volume of store, need install infrared sensor at the gate position of store, when someone passes through infrared sensor, infrared sensor can generate the count signal to statistics of the passenger flow volume of store, however, infrared sensor can not be the personnel that the distinguishment passes through and still be the customer, this also can lead to infrared sensor to count the staff that passes through, and it brings the error to count for the passenger flow volume statistics. When the passenger flow in the store is counted through monitoring, a merchant can only make a manual judgment on the passenger flow through the monitoring video, but the specific numerical value of the passenger flow cannot be determined, so that the merchant cannot accurately know the passenger flow of the store.
In order to solve the above problem, as shown in fig. 1, the present application provides a statistical method for passenger flow based on speech recognition, including:
s101, acquiring a voice set of a specified time period; voice information for recording voice sent by employees in the target store is contained in the voice set;
s102, searching target voice information containing the reception keywords from the voice set;
and S103, determining the passenger flow in the specified time period according to the recording time of the target voice information.
In the step S101, the time threshold of the statistical requirement is reflected in the specified time period, and only the passenger volume counted in the time threshold is calculated as the effective passenger volume, so that the present application can collect only the voice information of the voice uttered by the employee in the target store in the specified time period. The designated time period is specified by human, and may be 12 hours, one day, one week, one month, etc., and the application is not limited thereto.
Because the scheme is used for counting the passenger flow of the target store, the voice set reflects the voice information of the staff in the target store (the scheme is used for counting the passenger flow of the target store, the staff can be only a reception staff, and the identity characteristics of the staff can be determined according to the actual use scene), the voice information is sent by the staff, and the voice information sent by all the staff in the target store is combined into the voice set. The voice generated by the employee may be obtained by wearing a voice obtaining device (such as a mobile terminal with a microphone, etc., which is not limited herein) on the employee.
The voice set in the scheme can also be all voice information occurring at the store reception place, including the voice of the staff and the voice of the customer, and when the voice information is processed, the reception keywords in the voice information are identified, such as "welcome", which are the types of reception keywords that are unlikely to come from the customer, so that the statistics of the number of the customers can also be realized. In addition, the reception keyword can be set as 'n customers, please receive', and the quantity word n is identified and counted, so that accurate quantity statistics of multiple customers who enter the store at the same time is further ensured.
In step S102, the reception keyword reflects a statistical object of the statistical requirement, and the more the reception keyword occurs, the larger the passenger flow volume is, the less the reception keyword occurs, and the smaller the passenger flow volume is. The reception keyword may be "welcome", "welcome you", etc., and the application is not limited herein.
Specifically, when the target voice information including the keyword is searched in the voice set, the more the searched target voice information is, the larger the passenger flow volume is, the less the searched target voice information is, and the smaller the passenger flow volume is. It should be noted that when determining the target voice information, for each voice information, only when at least one reception keyword appears in the voice information, the voice information is determined to be the target voice information. When a plurality of reception keywords appear in one voice message, the voice message is also determined as only one target voice message.
For example, 500 pieces of voice information are in total in the voice set, 450 pieces of voice information containing the reception keywords are screened out from the voice set by using the reception keywords, and then it is determined that 450 pieces of target voice information are in total in the voice set.
In the above step S103, the number of target voice messages is counted, and the number of target voice messages is the passenger flow volume of the target store in the specified time period.
Continuing with the example of determining the target voice information, if it is determined that there are 450 target voice information in the voice set, it indicates that the employee has 450 clients to take over, i.e. the passenger flow is 450.
In the three steps, the voice information of the target store staff in the specified time period is obtained, the target voice information containing the reception keywords is searched in all the voice information, and the passenger flow in the specified time period is determined according to the number of the target voice information. The passenger flow volume is counted by acquiring the voice information of the staff, the staff and the clients can be accurately distinguished, the passenger flow volume obtained through counting does not contain the number of the staff, and the passenger flow volume counting accuracy is improved.
The voice sent by the employee acquired in the application may include two types: the first is a voice having a duration equal to that of a specified time period; the second is a voice whose duration is shorter than the duration of a specified period of time and which occurs within the specified period of time.
For the first voice, in order to determine the number of customers to be received by the employee in the voice, the following steps may be adopted to achieve the acquisition of the voice information:
step 1011, acquiring voice data of each employee in the target store within the specified time period;
step 1012, the voice data is divided into at least one voice message using the dialog blank threshold.
In the above step 1011, the voice data is voice having a duration equal to that of the specified period.
In step 1012, the dialog blank reflects that the employee did not speak in the current state, and if the dialog blank exists in the voice corresponding to the employee, it indicates that two sections of dialog are spoken between the employee and the client. The longer the session blank time, the more likely the employee will have a chance to pick up two customers, so the present application sets a session blank threshold (the session control threshold may be manually specified, and may be 15 seconds, 30 seconds, 1 minute, etc., and the present application is not limited herein). When the conversation blank time between two sections of conversations exceeds a conversation blank threshold value in the voice data, the staff is indicated to take hold of two groups of customers; and when the dialogue blank time between two sections of dialogue does not exceed the dialogue blank threshold value in the voice data, the staff is indicated to take hold of a group of customers. And dividing the voice data into at least one voice message through a dialogue blank threshold value so as to count the number of the staff receiving the clients.
For example, the voice data uttered by the employee is a 10-hour voice, the threshold of the dialog blanks is 30 seconds, and there are 100 dialog blanks in the 10-hour voice, where the duration of 24 dialog blanks is less than or equal to 30 seconds, and the duration of 76 dialog blanks is greater than 30 seconds, and then the 10-hour voice is divided by using the dialog blanks whose duration is greater than 30 seconds, so as to generate 77 pieces of voice information.
For the second voice, it may be intercepted by a mobile device worn by the employee. When the mobile device detects that the employee is in a conversation blank state (i.e. the employee does not speak within a conversation blank threshold), the mobile device stops acquiring the voice of the employee; when the mobile device detects that the employee is in a conversation state, the voice of the employee can be automatically acquired. Therefore, the mobile device acquires a voice having a duration shorter than the duration of the specified time period.
For example, when the mobile device detects the voice of the employee, the mobile device starts recording the voice, and stops recording the voice until the mobile device detects a 30-second dialog blank, and stores the voice as a voice message.
The use environment where the scheme of this application is located may be a relatively noisy environment (such as a restaurant), and the voice that the staff of acquireing sends may have certain noise (for example, the voice of other staff, the voice that the customer sent etc.) in order to more accurate statistics the passenger flow volume of target store, need carry out noise reduction to the voice that the staff of acquireing sent, and the processing procedure that above-mentioned staff sent the pronunciation includes the following step:
acquiring the voice to be processed corresponding to each employee in the target store within the specified time period;
and aiming at the voice to be processed corresponding to each employee, denoising the voice to be processed so as to screen out the voice corresponding to the employee.
Specifically, the method for performing noise reduction processing on the speech may include the following three steps: and voice noise reduction is carried out by utilizing artificial intelligence, voice noise reduction is carried out by utilizing a filter, and voice noise reduction is carried out by utilizing a spectral subtraction method.
After determining the passenger flow volume in the specified time period, as shown in fig. 2, the present application further provides a method for determining an operation policy, where the method includes:
s104, determining the peak time of the passenger flow according to the passenger flow volume of each time interval;
and S105, determining the operation strategy of the target store according to the passenger flow peak time.
In the above step S104, the time interval reflects the unit time of the statistical passenger flow volume, the time interval may be manually specified, and the time interval may be 1 minute, 3 minutes, and the like, and the present application is not limited herein. Multiple consecutive periods may be included within a given time period. The peak traffic hours reflect periods of high traffic.
Specifically, corresponding passenger flow is provided in each time interval, the time interval exceeding the preset passenger flow is screened out according to the passenger flow in each time interval, and the screened time interval is used as the passenger flow peak time interval.
For example, the specified time period is from 8 to 20 business hours of the target store, 1 hour is a time period, the traffic in each time period is 120, 115, 50, 130, 138, 140, 70, 20, 80, 100, 91 respectively, the traffic in each time period is considered to be large when the traffic exceeds 100, the traffic threshold value is set to 100, and the traffic peak time period when the traffic threshold value is exceeded is a traffic peak time period, the traffic peak time period of the target store in the specified time period is from 8 to 10, from 11 to 14, and from 18 to 19.
In the above step S105, the operation policy may be that the merchant changes the corresponding operation schedule according to the change of the passenger flow volume within a specified time period. In step S105, the operation policy may include one or more of the following: determining the scheduling rules of the employees in the target store according to the passenger flow peak time period; or determining the marketing plan of the target store according to the passenger flow peak time. The scheduling rule may be that more employees are arranged to serve the clients during the peak time of the passenger flow, and less employees are arranged to serve the clients during the non-peak time of the passenger flow, so that the employees can take more rest. The marketing plan can be used for simultaneously marketing products by using a plurality of means (such as an advertisement screen, broadcasting and the like) in the passenger flow peak time period, and marketing the products by using less means (only one or two means) in the non-passenger flow peak time period, so that the consumption of resources can be reduced, and the influence of the products is also improved.
Continuing with the above example of determining the peak time of passenger flow, the operation policy is to schedule the working hours of employees, after the peak time of passenger flow is determined, 20 employees can be scheduled to serve the customers in three time periods from 8 o 'clock to 10 o' clock, from 11 o 'clock to 14 o' clock, and from 18 o 'clock to 19 o' clock, and 10 employees are scheduled to serve the customers in the time periods from 10 o 'clock to 11 o' clock, and from 14 o 'clock to 18 o' clock.
After the peak time of the passenger flow is determined, some peak time of the passenger flow are distributed more closely, some peak time of the passenger flow are distributed more discretely, in order to make the operation policy arrangement of the target store more reasonable, after step S104, before step S105, further comprising:
and adjusting the time range of each passenger flow peak period according to the tightness degree of the time distribution of the passenger flow peak period.
The degree of closeness reflects the time distribution of the peak time of the passenger flow, the closer the distribution of the peak time of the passenger flow, the more likely the time interval between two peak time of the passenger flow becomes the peak time of the passenger flow, and the more discrete the distribution of the peak time of the passenger flow, the less likely the time interval between two peak time of the passenger flow becomes the peak time of the passenger flow. Therefore, the time of the passenger flow peak time can be adjusted by setting the preset duration of the time interval, and the two passenger flow peak time intervals with the time interval smaller than the preset duration are combined, so that the time range of the combined passenger flow peak time interval is from the starting time of the first passenger flow peak time interval to the ending time of the second passenger flow peak time interval.
For example, 4 peak time periods of traffic flow, the time range of the peak time period a is 8 to 9, the time range of the peak time period B is 11 to 12 to 50, the time range of the peak time period C is 13 to 14, the time range of the peak time period D is 15 to 17, the preset time of the time interval is 30 minutes, it can be determined that the time interval between the peak time period a and the peak time period B, and the time interval between the peak time period C and the peak time period D is much longer than the preset time, only the time interval between the peak time period B and the peak time period C is 10 minutes and is much shorter than the preset time, the time range of the peak time period B is adjusted, the ending time of the time range corresponding to the peak time period B is adjusted to the ending time of the peak time period C, and the time range of the peak time period B is 11 to 14, and deleting the original passenger flow peak time C.
The target voice information is acquired and needs to be searched in a voice set through keywords, and the searching mode comprises two modes:
first, in step S102, the method includes:
converting each voice message in the voice set into a voice text;
and inputting each voice text into the trained keyword recognition model to determine target voice information containing the reception keyword.
The meaning expressed by the text content of the voice text is consistent with the meaning expressed by the voice information. When converting voice information into voice text, a voice recognition engine is required. Because of the great sophistication of chinese characters, one pinyin may correspond to multiple characters (e.g., pinyin "shuijiao" which may be translated into "sleeping" or "dumpling"), and thus, in order to improve the accuracy of voice-to-text conversion, the present application needs to perform targeted training on the voice recognition engine (e.g., when the target store is a restaurant, the voice recognition engine needs to be trained with keywords corresponding to the dining room environment, or when the target store is a clothing store, the voice recognition engine needs to be trained with keywords corresponding to the clothing store environment, etc.).
And the keyword recognition model is used for recognizing keywords in the voice text, and after the trained keyword recognition model recognizes the keywords in the voice text, the voice information corresponding to the voice text is determined as the target voice information.
The keyword recognition model in the application is constructed by the following steps:
acquiring a sample set; the sample set comprises a positive sample and a negative sample; wherein, the positive sample can be a text sample, and the negative sample can be a keyword;
and simultaneously inputting the positive sample and the negative sample into the keyword recognition model to be trained so as to train the keyword recognition model to be trained.
Secondly, step S102 includes: and identifying whether preset keyword audio exists in each voice message, and if the preset keyword audio exists in the voice message, determining that the voice message is the target voice message.
According to the scheme, the passenger flow in the appointed time period is determined by obtaining the voice set of the staff in the target store and screening the target voice information from the voice set through the keywords, the condition that the staff is mistaken for the client is reduced, and the accuracy of passenger flow statistics is improved. The passenger flow peak time is determined according to the passenger flow volume of each time, so that a merchant determines the operation strategy of a target store according to the passenger flow peak time, more labor force and propaganda resources are invested in the passenger flow peak time, less labor force and propaganda resources are invested in the non-passenger flow peak time, and the investment of the cost of the merchant is reduced. The time range of each passenger flow peak time period is adjusted by utilizing the tightness degree of the time distribution of the passenger flow peak time period, so that the distribution of the passenger flow peak time period is more regular, a merchant can conveniently plan according to the time distribution of the passenger flow peak time period, and the condition that the operation strategy arrangement is disordered due to excessive passenger flow peak time periods can be avoided. In the process of processing the voice sent by the staff, the voice sent by the staff is subjected to noise reduction processing, the condition that the voice information is inaccurately divided due to the influence of noise is reduced, the condition that keywords cannot be recognized due to the influence of the noise is also reduced, the accuracy of determining the target voice information is improved, and the accuracy of passenger flow volume statistics is further improved.
As shown in fig. 3, the present application further provides a statistical apparatus for passenger flow based on speech recognition, including:
an obtaining module 301, configured to obtain a voice set of a specified time period; voice information for recording voice sent by employees in the target store is contained in the voice set;
a searching module 302, configured to search for target voice information including a reception keyword from a voice set;
and the determining module 303 is configured to determine the passenger flow in the specified time period according to the searched target voice information.
Optionally, the statistical apparatus further includes: the system comprises a passenger flow peak time period determining module and an operation strategy determining module;
the passenger flow peak time period determining module is used for determining the passenger flow peak time period according to the passenger flow volume of each time period;
the operation policy determination module is configured to determine an operation policy of the target store according to the passenger flow peak time.
Optionally, the statistical apparatus further includes: an adjustment module;
the adjusting module is used for adjusting the time range of each passenger flow peak time according to the tightness degree of the time distribution of the passenger flow peak time.
Optionally, the operation policy includes any one or two of:
determining the scheduling rules of the employees in the target store according to the passenger flow peak time period; or determining the marketing plan of the target store according to the passenger flow peak time.
Optionally, the searching module 302, when searching for the target voice information containing the reception keyword from the voice set, includes:
converting each voice message in the voice set into a voice text;
and inputting each voice text into the trained keyword recognition model to determine target voice information containing the reception keyword.
Optionally, the obtaining module 301 obtains the voice information by the following steps:
acquiring voice data of each employee in the target store within the specified time period;
the speech data is divided into at least one speech message using a dialog blank threshold.
Optionally, in the obtaining module 301, the processing process of the voice uttered by the employee includes the following steps:
acquiring the voice to be processed corresponding to each employee in the target store within the specified time period;
and aiming at the voice to be processed corresponding to each employee, denoising the voice to be processed so as to screen out the voice corresponding to the employee.
Corresponding to the statistical method of passenger flow volume based on speech recognition in fig. 1, the embodiment of the present application further provides a computer device 400, as shown in fig. 4, the device includes a memory 401, a processor 402, and a computer program stored on the memory 401 and operable on the processor 402, wherein the processor 402 implements the steps of the statistical method of passenger flow volume based on speech recognition when executing the computer program.
Specifically, the memory 401 and the processor 402 can be general memories and general processors, which are not specifically limited herein, and when the processor 402 runs a computer program stored in the memory 401, the method for counting passenger flow based on voice recognition can be executed, so as to solve the problem of how to improve the accuracy of passenger flow counting in the prior art, determine the passenger flow in a specified time period by acquiring a voice set of employees in a target store and screening target voice information from the voice set through keywords, distinguish the employees from customers, reduce the situation that the employees are mistaken for customers, enable the counted passenger flow not to include the number of the employees, and improve the accuracy of the passenger flow counting.
Corresponding to the method for counting passenger flow based on speech recognition in fig. 1, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the method for counting passenger flow based on speech recognition.
Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, and the like, when a computer program on the storage medium is run, the method for counting the passenger flow based on voice recognition can be executed, so as to solve the problem of how to improve the accuracy of passenger flow counting in the prior art, determine the passenger flow in a specified time period by acquiring a voice set of employees in a target store and screening target voice information from the voice set through keywords, distinguish the employees from customers, reduce the situation that the employees are mistaken for customers, enable the counted passenger flow not to include the number of the employees, and improve the accuracy of the passenger flow counting.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus once an item is defined in one figure, it need not be further defined and explained in subsequent figures, and moreover, the terms "first", "second", "third", etc. are used merely to distinguish one description from another and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the present disclosure, which should be construed in light of the above teachings. Are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A statistical method of passenger flow based on voice recognition is characterized by comprising the following steps:
acquiring a voice set of a specified time period; voice information for recording voice sent by employees in the target store is contained in the voice set;
searching target voice information containing the reception keywords from the voice set;
and determining the passenger flow of the specified time period according to the searched target voice information.
2. The statistical method of claim 1, wherein the method further comprises:
determining the peak time of passenger flow according to the passenger flow volume of each time interval;
and determining the operation strategy of the target store according to the passenger flow peak time.
3. The statistical method of claim 2, wherein after the step of determining the peak period of passenger flow, before the step of determining the operating policy of the target store based on the peak period of passenger flow, further comprises:
and adjusting the time range of each passenger flow peak period according to the tightness degree of the time distribution of the passenger flow peak period.
4. The statistical method of claim 2, wherein the operational policies include any one or both of:
determining the scheduling rules of the employees in the target store according to the passenger flow peak time period; or determining the marketing plan of the target store according to the passenger flow peak time.
5. The statistical method of claim 1, wherein the searching for the target voice information containing the reception keyword from the voice set comprises:
converting each voice message in the voice set into a voice text;
and inputting each voice text into the trained keyword recognition model to determine target voice information containing the reception keyword.
6. The statistical method of claim 1, wherein the obtaining of the voice information is achieved by:
acquiring voice data of each employee in the target store within the specified time period;
the speech data is divided into at least one speech message using a dialog blank threshold.
7. A statistical method according to claim 1, characterized in that said processing of the speech uttered by the staff comprises the following steps:
acquiring the voice to be processed corresponding to each employee in the target store within the specified time period;
and aiming at the voice to be processed corresponding to each employee, denoising the voice to be processed so as to screen out the voice corresponding to the employee.
8. A statistical apparatus for passenger flow volume based on speech recognition, comprising:
the acquisition module is used for acquiring a voice set of a specified time period; voice information for recording voice sent by employees in the target store is contained in the voice set;
the searching module is used for searching target voice information containing the reception keywords from the voice set;
and the determining module is used for determining the passenger flow in the specified time period according to the searched target voice information.
9. 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 steps of the method of any of the preceding claims 1-7 are implemented by the processor when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, is adapted to carry out the steps of the method according to any one of the preceding claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911198405.XA CN110930990A (en) | 2019-11-29 | 2019-11-29 | Passenger flow volume statistical method, device, equipment and medium based on voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911198405.XA CN110930990A (en) | 2019-11-29 | 2019-11-29 | Passenger flow volume statistical method, device, equipment and medium based on voice recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110930990A true CN110930990A (en) | 2020-03-27 |
Family
ID=69846779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911198405.XA Pending CN110930990A (en) | 2019-11-29 | 2019-11-29 | Passenger flow volume statistical method, device, equipment and medium based on voice recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110930990A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734467A (en) * | 2020-12-31 | 2021-04-30 | 北京明略软件系统有限公司 | Passenger flow prediction method and system for offline service scene |
| CN112906592A (en) * | 2021-03-03 | 2021-06-04 | 新疆爱华盈通信息技术有限公司 | Passenger flow volume analysis method and system and electronic equipment |
| CN113240347A (en) * | 2021-06-17 | 2021-08-10 | 恩亿科(北京)数据科技有限公司 | Service behavior data analysis method, system, storage medium and electronic device |
| CN114495959A (en) * | 2021-12-14 | 2022-05-13 | 科大讯飞股份有限公司 | Voice enhancement method, device and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107341685A (en) * | 2017-05-24 | 2017-11-10 | 百度在线网络技术（北京）有限公司 | Data analysing method and device |
| CN107507045A (en) * | 2017-10-10 | 2017-12-22 | 南京思德展示科技股份有限公司 | Retail shop operation data acquisition analysis system |
| CN109493122A (en) * | 2018-10-22 | 2019-03-19 | 深圳市秦丝科技有限公司 | Passenger flow statistics analysis method, terminal and storage medium for solid shop |
-
2019
- 2019-11-29 CN CN201911198405.XA patent/CN110930990A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107341685A (en) * | 2017-05-24 | 2017-11-10 | 百度在线网络技术（北京）有限公司 | Data analysing method and device |
| CN107507045A (en) * | 2017-10-10 | 2017-12-22 | 南京思德展示科技股份有限公司 | Retail shop operation data acquisition analysis system |
| CN109493122A (en) * | 2018-10-22 | 2019-03-19 | 深圳市秦丝科技有限公司 | Passenger flow statistics analysis method, terminal and storage medium for solid shop |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734467A (en) * | 2020-12-31 | 2021-04-30 | 北京明略软件系统有限公司 | Passenger flow prediction method and system for offline service scene |
| CN112906592A (en) * | 2021-03-03 | 2021-06-04 | 新疆爱华盈通信息技术有限公司 | Passenger flow volume analysis method and system and electronic equipment |
| CN113240347A (en) * | 2021-06-17 | 2021-08-10 | 恩亿科(北京)数据科技有限公司 | Service behavior data analysis method, system, storage medium and electronic device |
| CN114495959A (en) * | 2021-12-14 | 2022-05-13 | 科大讯飞股份有限公司 | Voice enhancement method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110930990A (en) | Passenger flow volume statistical method, device, equipment and medium based on voice recognition | |
| CN110910901B (en) | Emotion recognition method and device, electronic equipment and readable storage medium | |
| EP2727104B1 (en) | Identifying people that are proximate to a mobile device user via social graphs, speech models, and user context | |
| US10643620B2 (en) | Speech recognition method and apparatus using device information | |
| CN108986830B (en) | Audio corpus screening method and device | |
| CN109256136A (en) | A kind of audio recognition method and device | |
| US11245791B2 (en) | Detecting robocalls using biometric voice fingerprints | |
| CN110265040A (en) | Training method, device, storage medium and the electronic equipment of sound-groove model | |
| US20110282666A1 (en) | Utterance state detection device and utterance state detection method | |
| CN110070857B (en) | Model parameter adjusting method and device of voice awakening model and voice equipment | |
| CN110544469B (en) | Training method and device of voice recognition model, storage medium and electronic device | |
| CN111028834B (en) | Voice message reminding method and device, server and voice message reminding equipment | |
| US10769648B2 (en) | Automated business reviews based on patron sentiment | |
| CN111091832A (en) | Intention assessment method and system based on voice recognition | |
| CN110705309B (en) | Service quality evaluation method and system | |
| EP4371027A1 (en) | Intelligent task completion detection at a computing device | |
| CN108962243A (en) | arrival reminding method and device, mobile terminal and computer readable storage medium | |
| WO2021135140A1 (en) | Word collection method matching emotion polarity | |
| WO2018087967A1 (en) | Information processing device and information processing method | |
| CN110880081A (en) | Employee management method and device based on voice recognition, computer equipment and medium | |
| JP2013115622A (en) | Sound information analyzing apparatus and sound information analysis program | |
| CN114969295A (en) | Dialog interaction data processing method, device and equipment based on artificial intelligence | |
| CN114092264A (en) | Intelligent passenger obtaining method, system and electronic equipment | |
| CN113808709A (en) | Text analysis-based psychoelasticity prediction method and system | |
| CN109961778A (en) | The method and system of audio data intelligence quality inspection |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200327 |