CN112232737A - Purchase-sales-inventory processing method based on voice recognition - Google Patents
Purchase-sales-inventory processing method based on voice recognition Download PDFInfo
- Publication number
- CN112232737A CN112232737A CN202011103114.0A CN202011103114A CN112232737A CN 112232737 A CN112232737 A CN 112232737A CN 202011103114 A CN202011103114 A CN 202011103114A CN 112232737 A CN112232737 A CN 112232737A
- Authority
- CN
- China
- Prior art keywords
- client
- commodity
- information
- user
- voice
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 15
- 230000002457 bidirectional effect Effects 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 9
- 230000001960 triggered effect Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 9
- 238000013459 approach Methods 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 8
- 238000012790 confirmation Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 3
- 244000000626 Daucus carota Species 0.000 description 2
- 235000002767 Daucus carota Nutrition 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 230000003252 repetitive effect Effects 0.000 description 2
- 241001672694 Citrus reticulata Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 235000013410 fast food Nutrition 0.000 description 1
- 239000013067 intermediate product Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a purchase, sales and inventory processing method based on voice recognition, wherein a client records user voice, the voice is transmitted to a server in a text form after being preprocessed, the server sends the voice to a database by taking the ID of the current client as a serial number after being verified, the database recognizes commodity information, if commodities matched with the commodity information exist, the commodity information is recorded into the items of the current commodities, data is updated, information is fed back, and the commodities are confirmed by a user. The invention can realize the business processing of quickly adding purchase orders, warehousing orders, checking and the like, automatically identify the commodities required by the user, successfully and accurately approach the user requirements when the matching degree is highest, and help the user to save the time consumed in repeated labor. The invention saves the labor cost, lightens the labor intensity of supply chain service personnel and saves the time; complexity of multiple operation steps is simplified, and user experience is improved; the user adopts the command mode to process the business, and the purchase, sale and inventory can be completed by voice input, so that the user enthusiasm is improved.
Description
Technical Field
The present invention relates to data processing systems or methods particularly suited for administrative, commercial, financial, management, supervisory or forecasting purposes; the technical field of processing systems or methods specifically adapted for administrative, commercial, financial, administrative, supervisory or forecasting purposes, not otherwise provided for, and in particular to a purchase, sales and inventory processing method based on speech recognition.
Background
The supply chain refers to a functional network structure which is formed by forming intermediate products and final products from kit parts around a core enterprise, and finally sending the products to consumers from a sales network, and connecting suppliers, manufacturers, distributors and end users into a whole. The purchase-sale-storage, also called as purchase-sale chain, refers to the dynamic management process of purchase (in) -warehousing (storage) -sale (sale) in the enterprise management process, and is the key of the whole supply chain.
In most industries, special people specially take charge of purchase, sale and storage, the management is reasonable, and with the development of computer networks, an ERP system or at least office software is generally adopted for making tables and recording, and the arrangement is clear.
However, in the catering industry with a low access threshold, particularly in small catering, such as fast food restaurants and small restaurants, it is difficult for a practitioner to truly utilize an ERP system or office software to perform purchase, sale, storage and storage processing, when a service worker processes business documents such as purchasing, distribution, warehousing, returning, checking, adjustment and the like, since each document needs to be added with a large number of commodities, and each commodity needs to undergo four operation steps of selecting from searching, confirming units and confirming quantity, each step can further increase the workload due to an error, and then a large amount of complicated and repetitive labor is generated, which is time-consuming, labor-consuming and inconvenient; when the management is performed by hiring special personnel, although the problem can be solved temporarily, additional expenditure is caused, pressure is brought to small-scale catering practitioners, and the problem of multi-aspect management of personnel also exists.
Disclosure of Invention
The invention solves the problems that in the prior art, practitioners in the catering industry are easy to encounter a large amount of complicated and repetitive labor in the purchase, sale and stock process, or encounter personnel management obstacles and cost increase, and provides an optimized purchase, sale and stock processing method based on voice recognition.
The technical scheme adopted by the invention is that a purchase, sales and inventory processing method based on voice recognition comprises the following steps:
step 1: installing a client and configuring the client and a server;
step 2: the client detects user selection; if receiving the user instruction, prompting the standard voice input format, carrying out the next step, otherwise, repeating the step 2;
and step 3: recording the voice of the user, and starting recording at the client;
and 4, step 4: if receiving a user ending instruction, the client backups the voice information input by the user, and carries out the next step, otherwise, the step 3 is repeated;
and 5: preprocessing the voice information, and transmitting the preprocessed information to a server in a text form;
step 6: the server obtains the preprocessed information, takes the ID of the current client as a serial number and sends the serial number to the database;
and 7: the database identifies commodity information according to the preprocessed information, if a commodity matched with the commodity information is found under the ID of the current client, the commodity information is recorded into an item of the current commodity, data is updated, information is fed back to the corresponding client through the server, and the step 9 is carried out, otherwise, the next step is carried out;
and 8: searching a to-be-determined commodity catalog based on the commodity information, feeding back information to a corresponding client through a server, after a user selects accurate commodity information, enabling the database to find a commodity matched with the commodity information under the ID of the current client, inputting the commodity information into an item of the current commodity, updating data, feeding back the information to the corresponding client through the server, and carrying out the next step; if the user does not find accurate commodity information, performing step 10;
and step 9: if the user confirms the information, returning to the step 2 or stopping the machine, otherwise, carrying out the next step;
step 10: the client side backups the voice information backed up in the step 4 again and returns to the step 5 with the newly backed up voice information.
Preferably, the step 1 comprises the steps of:
step 1.1: a user installs a client on an intelligent terminal and starts the client;
step 1.2: operating the client to select languages and languages families;
step 1.3: configuring a port of a client to be in communication connection with an interface of a server, and distributing a private key for the client by the server;
step 1.4: the server stores the selection information of the current client;
step 1.5: and (3) testing the functions of the microphone and the power amplifier, if the functions are normal, performing the step (2), otherwise, completing the prompt function, and repeating the step (1.5) after the user adjusts the functions.
Preferably, in step 2, the user instruction includes a purchase instruction as an entry, a sale instruction as an sale item, and a warehousing instruction as an entry; the user instruction is triggered by voice collection or selection.
Preferably, in step 2, the standard voice entry format is prompted through voice and/or interface text.
Preferably, in step 4, the ending instruction is triggered by voice collection or selection.
Preferably, step 5 comprises the steps of:
step 5.1: inputting the voice information into a convolution denoising automatic encoder to carry out noise filtering;
step 5.2: calling information preset and configured by a user for the output voice to perform initial identification, and converting the voice content into characters corresponding to the configuration information;
step 5.3: establishing a time axis according to the corresponding relation between the characters and the voice, and initially segmenting the characters by pause in the voice;
step 5.4: based on the initial segmentation, comparing the characters with a word bank, and matching a plurality of replaceable words for each segment of characters;
step 5.5: and inputting the preprocessed characters and the corresponding replaceable words into a text file, encrypting the text file by using a private key, and transmitting the text file to a server by using the ID of the current client as a file name.
Preferably, in step 6, the server obtains the encrypted text transmitted by the client, decrypts the encrypted text with the corresponding private key of the current client, and sends the encrypted text to the database with the ID of the current client as the serial number if decryption is successful, otherwise, discards the current encrypted text, and feeds back an error, and then performs step 2.
Preferably, in step 7, the commodity information identified by the database includes a commodity name, a quantity, and a measurement unit corresponding to the commodity.
Preferably, said step 7 comprises the steps of:
step 7.1: the database obtains the ID of the current client as a serial number, and a commodity list under the current ID is called;
step 7.2: the database compares the current commodity names in the commodity list, if the commodities with the same commodity names are compared, the next step is carried out, and if not, the step 8 is carried out;
step 7.3: acquiring a reasonable quantity range of the current matched commodities under the current user instruction and a plurality of reasonable metering units corresponding to the commodities in a database, if the quantity of the current commodity information falls into the range and the metering units are reasonable, recording the commodity information into an item of the current commodity, updating data, feeding back information to a corresponding client through a server, and performing the step 9, otherwise, performing the next step;
step 7.4: the server feeds back alarm information to the client and displays data abnormity through a popup window; if the user confirms that the error occurs, error information is fed back, accurate measurement units are input by voice or manually, after the client and the database are confirmed in a bidirectional mode, the user inputs accurate quantity by voice or manually, and the client and the database are confirmed in a bidirectional mode again;
step 7.5: the client inputs the key, the server verifies the key, the database updates the data, and the server feeds back information to the corresponding client, and step 9 is performed.
Preferably, step 8 comprises the steps of:
step 8.1: comparing the replaceable words in the commodity list, if the commodity with the matched commodity name is obtained through comparison, recording a to-be-determined commodity catalog, and performing the step 8.3, and if no matched commodity exists, performing the next step;
step 8.2: respectively splitting the currently recognized commodity name and the replaceable word into a plurality of single words, matching a commodity list of the database with any single word, and after duplication removal, recording all matched commodities into a pending commodity catalog;
step 8.3: feeding back the to-be-determined commodity catalog to the corresponding client through the server, if the user finds out an accurate commodity name, performing the next step, and if not, performing the step 10;
step 8.4: the database searches a reasonable quantity range and a plurality of reasonable metering units corresponding to the commodities under the instruction of the user according to the commodity name selected by the user, if the quantity of the current commodity information falls into the range and the metering units are reasonable, the commodity information is recorded into the item of the current commodity, the data is updated, the information is fed back to the corresponding client through the server, and the step 9 is carried out, otherwise, the next step is carried out;
step 8.5: the server feeds back alarm information to the client and displays data abnormity through a popup window; if the user confirms that the error occurs, error information is fed back, accurate measurement units are input by voice or manually, after the client and the database are confirmed in a bidirectional mode, the user inputs accurate quantity by voice or manually, and the client and the database are confirmed in a bidirectional mode again;
step 8.6: the client inputs the key, the server verifies the key, the database updates the data, and the server feeds back information to the corresponding client, and step 9 is performed.
The invention provides an optimized purchase, sales and inventory processing method based on voice recognition, wherein a client records voice of a user after receiving a user instruction, voice information is transmitted to a server in a text form after being preprocessed, the server takes the ID of the current client as a serial number after being verified, the serial number is sent to a database, the database recognizes commodity information according to the preprocessed information, if a commodity matched with the commodity information is found under the ID of the current client or the commodity matched with the commodity information is found in a pending commodity catalog, the commodity information is recorded into an item of the current commodity, data is updated, information is fed back to the corresponding client through the server, and the information is submitted to the user for confirmation. The invention can realize the business processing of quickly adding purchase orders, warehousing orders, checking and the like, automatically identify the commodities required by the user, successfully and accurately approach the user requirements when the matching degree is highest, and help the user to save the time consumed in repeated labor.
The invention has the beneficial effects that:
(1) the restaurant can save the labor cost, reduce the labor intensity of supply chain business personnel and save at least 50 percent of time under the condition of the same commodity quantity;
(2) the complexity of multiple operation steps is simplified, five steps of operation are combined into one step, and the user experience is improved;
(3) the user adopts the command mode to process the business, and can finish the purchase, sale and inventory items only by voice input basically, thereby improving the user enthusiasm.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention is described in further detail with reference to the following examples, but the scope of the present invention is not limited thereto.
The invention relates to a purchase-sales-inventory processing method based on voice recognition, which comprises the following steps.
Step 1: and installing the client and configuring the client and the server.
The step 1 comprises the following steps:
step 1.1: a user installs a client on an intelligent terminal and starts the client;
step 1.2: operating the client to select languages and languages families;
step 1.3: configuring a port of a client to be in communication connection with an interface of a server, and distributing a private key for the client by the server;
step 1.4: the server stores the selection information of the current client;
step 1.5: and (3) testing the functions of the microphone and the power amplifier, if the functions are normal, performing the step (2), otherwise, completing the prompt function, and repeating the step (1.5) after the user adjusts the functions.
In the invention, a user installs a client on an intelligent terminal, such as a mobile phone, and the client displays an operation interface to the user, such as a purchase order detail page, a delivery and delivery invoice detail page, a purchase warehousing entry detail page, a purchase return detail page, an inventory checking detail page, an inventory adjustment detail page and the like, wherein services related to the pages are included in the purchase, sales and inventory business.
In the invention, in the supply chain business document page, a user needs to perform high-frequency commodity adding operation according to the page prompt, and after the operation is finished, the client calls the corresponding data and business interface of the server end in real time to present the corresponding page content and result feedback and guide the client to complete the whole voice raw material adding process, so the port of the client is configured to be in communication connection with the interface of the server.
In the invention, the client can meet the requirement of selecting languages and language families by the user, the languages refer to languages of different countries and different regions such as Chinese, English, Japanese and the like, and the languages comprise Mandarin, Cantonese, Minnan and the like, certainly, in the long-term learning process, the expansion of the language families can be more diversified, and the language family template more suitable for the user is obtained by intercepting the voice and the intonation of the current user, extracting the characteristics and associating with the input commodity information, so that the input accuracy is improved, and the efficiency of voice recognition is further improved.
In the invention, the purchase, sale and storage are important links of a supply chain and relate to the goods in and out management of a user, so that the server distributes a private key for the client for verifying the user.
Step 2: the client detects user selection; if receiving the user instruction, prompting the standard voice input format, carrying out the next step, otherwise, repeating the step 2.
In the step 2, the user instruction comprises a purchase instruction as an input item, a sale instruction as an sale item and a warehousing instruction as an input item; the user instruction is triggered by voice collection or selection.
And in the step 2, prompting a standard voice input format through voice and/or interface characters.
In the invention, when a user enters a supply chain business document detail page such as a purchase order detail page, a purchase warehousing entry detail page, a purchase return order detail page and the like, a point touch button can be seen, point touch is kept, and voice is input.
In the present invention, generally, the standard voice entry format is "name of goods + type of service + number of goods + unit of goods".
And step 3: and (4) recording the voice of the user, and starting recording by the client.
And 4, step 4: if receiving the user end instruction, the client backups the voice information recorded by the user, and carries out the next step, otherwise, the step 3 is repeated.
In step 4, the ending instruction is triggered by voice collection or selection.
In the invention, in the page of the voice adding raw material, the user presses the microphone button to speak, and speaks the name, the number, the unit and other information of the commodity, and certainly, the user can confirm the speaking content according to personal preference, but inaccurate identification can be caused; and after the speaking is finished, the microphone button is released to finish the voice input.
In the invention, generally speaking, the user is advised to add pause properly in the voice input process so as to improve the accuracy of voice recognition and the accuracy of word segmentation.
In the invention, the voice information is backed up, and the next quick and accurate re-identification is ensured.
And 5: and preprocessing the voice information, and transmitting the preprocessed information to a server in a text form.
Step 5 comprises the following steps:
step 5.1: inputting the voice information into a convolution denoising automatic encoder to carry out noise filtering;
step 5.2: calling information preset and configured by a user for the output voice to perform initial identification, and converting the voice content into characters corresponding to the configuration information;
step 5.3: establishing a time axis according to the corresponding relation between the characters and the voice, and initially segmenting the characters by pause in the voice;
step 5.4: based on the initial segmentation, comparing the characters with a word bank, and matching a plurality of replaceable words for each segment of characters;
step 5.5: and inputting the preprocessed characters and the corresponding replaceable words into a text file, encrypting the text file by using a private key, and transmitting the text file to a server by using the ID of the current client as a file name.
In the invention, the voice information is preprocessed in the client, the preprocessing is mainly used for processing noise in the voice information, the voice information can be converted into more accurate characters only after the noise is removed, generally speaking contents of a user can be translated into characters by calling an interface of a voice and character conversion module, such as a conversion interface of a science news system, and the characters are transmitted to a server.
In the invention, in the conversion process, because the user is prompted to stop consciously, a time axis of characters and voice is established, the characters are segmented by stopping, and a plurality of replaceable words can be matched for each sentence break based on the segmented identification content, if fuzzy pronunciation exists, and each sentence break is generally 5 according to probability and weight.
In the invention, the private key distributed by the server is used for encrypting and packaging the text content including the replaceable words, and the ID of the client is used as the file name, so that the processing of the server is facilitated.
Step 6: and the server acquires the preprocessed information, takes the ID of the current client as a serial number and sends the serial number to the database.
In step 6, the server obtains the encrypted text transmitted by the client, decrypts the encrypted text by using the corresponding private key of the current client, if the decryption is successful, the ID of the current client is used as a serial number and is sent to the database, otherwise, the current encrypted text is thrown away, an error is fed back, and the step 2 is carried out.
In the invention, the server is a software component used for receiving the client data and the service request and returning the data and the service response to the client.
In the invention, the server searches the private key distributed to the client according to the ID of the client, tries to decrypt the file information from the client by using the private key, if the decryption is successful, the file information is represented as compliance information, and the next operation can be continued, otherwise, the file can be tampered or other unsafe information, and the client is required to check error information.
In the invention, the database can adopt SOLR and the like, and the server sends the characters and the shop information content to the SOLR for processing and then completes the subsequent matching and inputting process.
And 7: and the database identifies the commodity information according to the preprocessed information, if the commodity matched with the commodity information is found under the ID of the current client, the commodity information is recorded into the item of the current commodity, the data is updated, the information is fed back to the corresponding client through the server, and the step 9 is carried out, otherwise, the next step is carried out.
In step 7, the commodity information identified by the database includes the name and number of the commodity and the metering unit corresponding to the commodity.
The step 7 comprises the following steps:
step 7.1: the database obtains the ID of the current client as a serial number, and a commodity list under the current ID is called;
step 7.2: the database compares the current commodity names in the commodity list, if the commodities with the same commodity names are compared, the next step is carried out, and if not, the step 8 is carried out;
step 7.3: acquiring a reasonable quantity range of the current matched commodities under the current user instruction and a plurality of reasonable metering units corresponding to the commodities in a database, if the quantity of the current commodity information falls into the range and the metering units are reasonable, recording the commodity information into an item of the current commodity, updating data, feeding back information to a corresponding client through a server, and performing the step 9, otherwise, performing the next step;
step 7.4: the server feeds back alarm information to the client and displays data abnormity through a popup window; if the user confirms that the error occurs, error information is fed back, accurate measurement units are input by voice or manually, after the client and the database are confirmed in a bidirectional mode, the user inputs accurate quantity by voice or manually, and the client and the database are confirmed in a bidirectional mode again;
step 7.5: the client inputs the key, the server verifies the key, the database updates the data, and the server feeds back information to the corresponding client, and step 9 is performed.
And 8: searching a to-be-determined commodity catalog based on the commodity information, feeding back information to a corresponding client through a server, after a user selects accurate commodity information, enabling the database to find a commodity matched with the commodity information under the ID of the current client, inputting the commodity information into an item of the current commodity, updating data, feeding back the information to the corresponding client through the server, and carrying out the next step; if the user does not find accurate commodity information, step 10 is performed.
Step 8 comprises the following steps:
step 8.1: comparing the replaceable words in the commodity list, if the commodity with the matched commodity name is obtained through comparison, recording a to-be-determined commodity catalog, and performing the step 8.3, and if no matched commodity exists, performing the next step;
step 8.2: respectively splitting the currently recognized commodity name and the replaceable word into a plurality of single words, matching a commodity list of the database with any single word, and after duplication removal, recording all matched commodities into a pending commodity catalog;
step 8.3: feeding back the to-be-determined commodity catalog to the corresponding client through the server, if the user finds out an accurate commodity name, performing the next step, and if not, performing the step 10;
step 8.4: the database searches a reasonable quantity range and a plurality of reasonable metering units corresponding to the commodities under the instruction of the user according to the commodity name selected by the user, if the quantity of the current commodity information falls into the range and the metering units are reasonable, the commodity information is recorded into the item of the current commodity, the data is updated, the information is fed back to the corresponding client through the server, and the step 9 is carried out, otherwise, the next step is carried out;
step 8.5: the server feeds back alarm information to the client and displays data abnormity through a popup window; if the user confirms that the error occurs, error information is fed back, accurate measurement units are input by voice or manually, after the client and the database are confirmed in a bidirectional mode, the user inputs accurate quantity by voice or manually, and the client and the database are confirmed in a bidirectional mode again;
step 8.6: the client inputs the key, the server verifies the key, the database updates the data, and the server feeds back information to the corresponding client, and step 9 is performed.
In the invention, taking SOLR as an example, after receiving the voice content and the shop information, analyzing the character information to split the commodity information in the character information; the commodity information includes, but is not limited to, commodity names, quantity and metering units corresponding to the commodities, and the commodity information is bound with the ID of the client, namely, the commodity information can be matched and identified in a commodity list corresponding to the client, and commodities meeting conditions are found.
In the invention, if the commodity name is definite, the quantity falls into a reasonable range and the metering unit is reasonable, the commodity information is recorded into the item of the current commodity, the data is updated, and the information is fed back to the corresponding client through the server, otherwise, an error obviously exists. For example, the measurement unit of carrot in the database is jin, the voice recognition result of the user is that carrot 20 is played, although the commodity name corresponds, the quantity and the measurement unit cannot be matched, and further confirmation is needed.
In the invention, simple errors can be directly confirmed by a user, accurate metering units are firstly confirmed, accurate quantity is input after bidirectional confirmation is carried out between the client and the database, after confirmation, the user inputs a secret key and the server verifies the correctness, releases the validity, the database updates data, and information is fed back to the corresponding client through the server.
In the invention, the bidirectional confirmation of the client and the database means that the input of the client is accepted by the database, and the feedback of the database is accepted by the client.
In the invention, commodities with unmatched commodity information comprise the situations that commodities are not found and a plurality of commodities are found; comparing the replaceable words in the commodity list, and if the commodity with the same commodity name is compared, recording a to-be-determined commodity catalog, wherein the condition is that no commodity is found; or the currently recognized commodity name and the replaceable word are respectively split into a plurality of single words, any single word is matched with a commodity list of the database, after duplication is removed, all matched commodities are recorded in a pending commodity catalog, and the situation is that a plurality of commodities are found.
In the invention, the user confirms the accurate commodity name, the database actively matches whether the quantity in the commodity information and the corresponding metering unit fall within the reasonable acceptable range of the commodity name confirmed by the user, if so, the commodity is directly accepted, otherwise, the commodity is re-entered step by step, and if so, the commodity name is consistent with the metering unit in the step 7.
And step 9: and (5) returning to the step (2) or stopping the machine if the user confirms the information, or else, carrying out the next step.
Step 10: the client side backups the voice information backed up in the step 4 again and returns to the step 5 with the newly backed up voice information.
In the invention, when any commodity in the pending commodity catalog is not consistent, the commodity is required to be identified again; of course, the user may interrupt entry, supplementing the data in the database.
In the invention, a client records the voice of a user after receiving a user instruction, the voice information is preprocessed and then transmitted to a server in a text form, the server sends the serial number which is identified by taking the ID of the current client as a serial number to a database, the database identifies commodity information according to the preprocessed information, if a commodity which is matched with the commodity information is found under the ID of the current client or the commodity which is matched with the commodity information is found in a pending commodity catalog, the commodity information is recorded into an item of the current commodity, data is updated, the information is fed back to the corresponding client through the server, and the information is confirmed by the user. The invention can realize the business processing of quickly adding purchase orders, warehousing orders, checking and the like, automatically identify the commodities required by the user, successfully and accurately approach the user requirements when the matching degree is highest, and help the user to save the time consumed in repeated labor.
The invention has the advantages that the restaurant can save the labor cost, reduce the labor intensity of supply chain business personnel and save at least 50 percent of time under the condition of the same commodity quantity; the complexity of multiple operation steps is simplified, five steps of operation are combined into one step, and the user experience is improved; the user adopts the command mode to process the business, and can finish the purchase, sale and inventory items only by voice input basically, thereby improving the user enthusiasm.
Claims (10)
1. A purchase-sales-inventory processing method based on voice recognition is characterized by comprising the following steps: the method comprises the following steps:
step 1: installing a client and configuring the client and a server;
step 2: the client detects user selection; if receiving the user instruction, prompting the standard voice input format, carrying out the next step, otherwise, repeating the step 2;
and step 3: recording the voice of the user, and starting recording at the client;
and 4, step 4: if receiving a user ending instruction, the client backups the voice information input by the user, and carries out the next step, otherwise, the step 3 is repeated;
and 5: preprocessing the voice information, and transmitting the preprocessed information to a server in a text form;
step 6: the server obtains the preprocessed information, takes the ID of the current client as a serial number and sends the serial number to the database;
and 7: the database identifies commodity information according to the preprocessed information, if a commodity matched with the commodity information is found under the ID of the current client, the commodity information is recorded into an item of the current commodity, data is updated, information is fed back to the corresponding client through the server, and the step 9 is carried out, otherwise, the next step is carried out;
and 8: searching a to-be-determined commodity catalog based on the commodity information, feeding back information to a corresponding client through a server, after a user selects accurate commodity information, enabling the database to find a commodity matched with the commodity information under the ID of the current client, inputting the commodity information into an item of the current commodity, updating data, feeding back the information to the corresponding client through the server, and carrying out the next step; if the user does not find accurate commodity information, performing step 10;
and step 9: if the user confirms the information, returning to the step 2 or stopping the machine, otherwise, carrying out the next step;
step 10: the client side backups the voice information backed up in the step 4 again and returns to the step 5 with the newly backed up voice information.
2. The purchase-sale-stock processing method based on the voice recognition as claimed in claim 1, wherein: the step 1 comprises the following steps:
step 1.1: a user installs a client on an intelligent terminal and starts the client;
step 1.2: operating the client to select languages and languages families;
step 1.3: configuring a port of a client to be in communication connection with an interface of a server, and distributing a private key for the client by the server;
step 1.4: the server stores the selection information of the current client;
step 1.5: and (3) testing the functions of the microphone and the power amplifier, if the functions are normal, performing the step (2), otherwise, completing the prompt function, and repeating the step (1.5) after the user adjusts the functions.
3. The purchase-sale-stock processing method based on the voice recognition as claimed in claim 1, wherein: in the step 2, the user instruction comprises a purchase instruction as an input item, a sale instruction as an sale item and a warehousing instruction as an input item; the user instruction is triggered by voice collection or selection.
4. The purchase-sale-stock processing method based on the voice recognition as claimed in claim 1, wherein: and in the step 2, prompting a standard voice input format through voice and/or interface characters.
5. The purchase-sale-stock processing method based on the voice recognition as claimed in claim 1, wherein: in step 4, the ending instruction is triggered by voice collection or selection.
6. The purchase-sales-inventory processing method based on voice recognition according to claim 2, characterized in that: step 5 comprises the following steps:
step 5.1: inputting the voice information into a convolution denoising automatic encoder to carry out noise filtering;
step 5.2: calling information preset and configured by a user for the output voice to perform initial identification, and converting the voice content into characters corresponding to the configuration information;
step 5.3: establishing a time axis according to the corresponding relation between the characters and the voice, and initially segmenting the characters by pause in the voice;
step 5.4: based on the initial segmentation, comparing the characters with a word bank, and matching a plurality of replaceable words for each segment of characters;
step 5.5: and inputting the preprocessed characters and the corresponding replaceable words into a text file, encrypting the text file by using a private key, and transmitting the text file to a server by using the ID of the current client as a file name.
7. The purchase-sales-inventory processing method based on voice recognition according to claim 6, wherein: in step 6, the server obtains the encrypted text transmitted by the client, decrypts the encrypted text by using the corresponding private key of the current client, if the decryption is successful, the ID of the current client is used as a serial number and is sent to the database, otherwise, the current encrypted text is thrown away, an error is fed back, and the step 2 is carried out.
8. The purchase-sale-stock processing method based on the voice recognition as claimed in claim 1, wherein: in step 7, the commodity information identified by the database includes the name and number of the commodity and the metering unit corresponding to the commodity.
9. The purchase-sales-inventory processing method based on voice recognition according to claim 8, wherein: the step 7 comprises the following steps:
step 7.1: the database obtains the ID of the current client as a serial number, and a commodity list under the current ID is called;
step 7.2: the database compares the current commodity names in the commodity list, if the commodities with the same commodity names are compared, the next step is carried out, and if not, the step 8 is carried out;
step 7.3: acquiring a reasonable quantity range of the current matched commodities under the current user instruction and a plurality of reasonable metering units corresponding to the commodities in a database, if the quantity of the current commodity information falls into the range and the metering units are reasonable, recording the commodity information into an item of the current commodity, updating data, feeding back information to a corresponding client through a server, and performing the step 9, otherwise, performing the next step;
step 7.4: the server feeds back alarm information to the client and displays data abnormity through a popup window; if the user confirms that the error occurs, error information is fed back, accurate measurement units are input by voice or manually, after the client and the database are confirmed in a bidirectional mode, the user inputs accurate quantity by voice or manually, and the client and the database are confirmed in a bidirectional mode again;
step 7.5: the client inputs the key, the server verifies the key, the database updates the data, and the server feeds back information to the corresponding client, and step 9 is performed.
10. The purchase-sales-inventory processing method based on voice recognition according to claim 6, wherein: step 8 comprises the following steps:
step 8.1: comparing the replaceable words in the commodity list, if the commodity with the matched commodity name is obtained through comparison, recording a to-be-determined commodity catalog, and performing the step 8.3, and if no matched commodity exists, performing the next step;
step 8.2: respectively splitting the currently recognized commodity name and the replaceable word into a plurality of single words, matching a commodity list of the database with any single word, and after duplication removal, recording all matched commodities into a pending commodity catalog;
step 8.3: feeding back the to-be-determined commodity catalog to the corresponding client through the server, if the user finds out an accurate commodity name, performing the next step, and if not, performing the step 10;
step 8.4: the database searches a reasonable quantity range and a plurality of reasonable metering units corresponding to the commodities under the instruction of the user according to the commodity name selected by the user, if the quantity of the current commodity information falls into the range and the metering units are reasonable, the commodity information is recorded into the item of the current commodity, the data is updated, the information is fed back to the corresponding client through the server, and the step 9 is carried out, otherwise, the next step is carried out;
step 8.5: the server feeds back alarm information to the client and displays data abnormity through a popup window; if the user confirms that the error occurs, error information is fed back, accurate measurement units are input by voice or manually, after the client and the database are confirmed in a bidirectional mode, the user inputs accurate quantity by voice or manually, and the client and the database are confirmed in a bidirectional mode again;
step 8.6: the client inputs the key, the server verifies the key, the database updates the data, and the server feeds back information to the corresponding client, and step 9 is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011103114.0A CN112232737A (en) | 2020-10-15 | 2020-10-15 | Purchase-sales-inventory processing method based on voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011103114.0A CN112232737A (en) | 2020-10-15 | 2020-10-15 | Purchase-sales-inventory processing method based on voice recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112232737A true CN112232737A (en) | 2021-01-15 |
Family
ID=74113751
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011103114.0A Pending CN112232737A (en) | 2020-10-15 | 2020-10-15 | Purchase-sales-inventory processing method based on voice recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112232737A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116069818A (en) * | 2023-01-05 | 2023-05-05 | 广州市华势信息科技有限公司 | Application processing method and system based on zero code development |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003099092A (en) * | 2001-09-21 | 2003-04-04 | Chuo Joho Kaihatsu Kk | Voice input system using portable information terminal, and article management system for stocktaking or ordering and order reception using the same, inspection management system, visit care management system, and nursing management system |
| KR20080032813A (en) * | 2006-10-11 | 2008-04-16 | 에스케이 텔레콤주식회사 | Mobile commerce system using voice recognition server and method for the same |
| CN103870946A (en) * | 2014-03-18 | 2014-06-18 | 沈阳化工大学 | Supermarket invoicing system |
| CN104318414A (en) * | 2014-10-23 | 2015-01-28 | 沈阳化工大学 | Commodity inventory management information system |
| CN109003013A (en) * | 2017-09-20 | 2018-12-14 | 深圳市大掌柜商业智能有限公司 | A kind of business suspended method based on voice technology |
-
2020
- 2020-10-15 CN CN202011103114.0A patent/CN112232737A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003099092A (en) * | 2001-09-21 | 2003-04-04 | Chuo Joho Kaihatsu Kk | Voice input system using portable information terminal, and article management system for stocktaking or ordering and order reception using the same, inspection management system, visit care management system, and nursing management system |
| KR20080032813A (en) * | 2006-10-11 | 2008-04-16 | 에스케이 텔레콤주식회사 | Mobile commerce system using voice recognition server and method for the same |
| CN103870946A (en) * | 2014-03-18 | 2014-06-18 | 沈阳化工大学 | Supermarket invoicing system |
| CN104318414A (en) * | 2014-10-23 | 2015-01-28 | 沈阳化工大学 | Commodity inventory management information system |
| CN109003013A (en) * | 2017-09-20 | 2018-12-14 | 深圳市大掌柜商业智能有限公司 | A kind of business suspended method based on voice technology |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116069818A (en) * | 2023-01-05 | 2023-05-05 | 广州市华势信息科技有限公司 | Application processing method and system based on zero code development |
| CN116069818B (en) * | 2023-01-05 | 2023-09-12 | 广州市华势信息科技有限公司 | Application processing method and system based on zero code development |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20120330662A1 (en) | Input supporting system, method and program | |
| US8233751B2 (en) | Method and system for simplified recordkeeping including transcription and voting based verification | |
| US10074120B2 (en) | Dynamic template selector and data integrity engine for inspection reports | |
| CN106874134B (en) | Work order type processing method, device and system | |
| CN108305050B (en) | Method, device, equipment and medium for extracting report information and service demand information | |
| CN105657129A (en) | Call information obtaining method and device | |
| US20030004830A1 (en) | Carrier and package delivery desktop tools | |
| US20050108625A1 (en) | Method and system for selecting rules to validate information submitted on an electronic form | |
| US20110166934A1 (en) | Targeted advertising based on remote receipt analysis | |
| US20110052075A1 (en) | Remote receipt analysis | |
| US8589165B1 (en) | Free text matching system and method | |
| CN111597318A (en) | Method, device and system for executing business task | |
| US7813975B2 (en) | System and method for processing account data | |
| CN114841128B (en) | Business interaction method, device, equipment, medium and product based on artificial intelligence | |
| CN110837356A (en) | Data processing method and device | |
| CN111128160A (en) | Receipt modification method and device based on voice recognition and computer equipment | |
| CN112232737A (en) | Purchase-sales-inventory processing method based on voice recognition | |
| JP6899797B2 (en) | Inquiry device identification system, inquiry device identification method | |
| CN105740900A (en) | Information identification method and apparatus | |
| KR20120025322A (en) | Ordering system using smart phone | |
| CN117217699A (en) | Contract approval management system and method | |
| US20230125177A1 (en) | Methods and systems for matching and optimizing technology solutions to requested enterprise products | |
| CN111552779A (en) | Man-machine conversation method, device, medium and electronic equipment | |
| CN110570120A (en) | ERP intelligent ordering method, device, system and storage medium | |
| CN112131379A (en) | Method, device, electronic equipment and storage medium for identifying problem category |
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 |