Information entry method, device and electronic equipment

Abstract

The embodiment of the present application discloses an information entry method, device and electronic device, the method comprising: providing voice entry guidance information in a form entry interface; the voice entry guidance information includes multiple fill-in-the-blank items and guidance copy information; the guidance copy information is used to string the fill-in-the-blank items into a natural language paragraph, so as to perform voice input based on the natural language paragraph; perform voice recognition on the received voice input information; identify the to-be-entered content corresponding to the fill-in-the-blank item from the voice recognition result; determine the entry results of multiple fields in the target form according to the to-be-entered content and the corresponding relationship between the fill-in-the-blank item and the field in the target form. It can improve the efficiency of filling in form information in mobile office scenarios.

Description

Technical Field

[0001] The present application relates to the technical field of information entry, and in particular to an information entry method, device and electronic device. Background Art

[0002] Customer Relationship Management (CRM) is a system that helps companies maintain customer relationships. Without the help of such a system, sales staff in the company need to rely on their own accurate memory and image in their minds to complete customer portraits. This places high demands on the sales staff's memory ability. If the customer portrait is wrong, it will be difficult to cater to the customer's preferences, and it will be difficult to close a deal. The CRM customer relationship management system can help sales staff record the basic information of customers and the follow-up information of customers. Recording customer information through the system can help sales staff accurately portray. It is precisely because of the help of the CRM customer relationship management system that the company's sales staff can have more time to follow up with customers and promote sales.

[0003] Traditional CRM systems can provide users with PC pages or applications. However, with the development of mobile applications, many PC applications have been transferred to mobile devices, including the above-mentioned CRM systems. Since sales staff are working outside most of the time, their reliance on mobile applications is gradually increasing. Among them, a frequently used scenario is entering visit forms. A salesperson may need to visit 5-6 or even more customers every day. According to company regulations and other requirements, after each visit, the visit form must be entered into the CRM system to be considered an effective visit.

[0004] In existing mobile CRM applications, the page for entering a visit form usually lists multiple fields from top to bottom, and sales staff need to fill them out one by one. Therefore, the problem commonly reported by sales staff is that there are too many fields, and each item needs to be filled out / selected manually, resulting in low efficiency and a long overall time consumption, which does not meet the convenient characteristics of wireless mobile office. In addition to the visit form entry scenario in the above CRM system, similar situations also exist in other mobile office scenarios.

[0005] Therefore, how to improve the efficiency of form filling in mobile office scenarios has become a technical problem that needs to be solved by technical personnel in this field. Summary of the invention

[0006] The present application provides an information entry method, device and electronic device, which can improve the efficiency of form filling in mobile office scenarios.

[0007] This application provides the following solutions:

[0008] An information entry method, comprising:

[0009] Providing voice input guidance information in the form input interface; the voice input guidance information includes a plurality of fill-in-the-blank items and guidance copy information; the guidance copy information is used to string the fill-in-the-blank items into a natural language paragraph, so as to perform voice input based on the natural language paragraph;

[0010] Performing speech recognition on the received speech input information;

[0011] Identifying the content to be entered corresponding to the fill-in-the-blank item from the speech recognition result;

[0012] According to the content to be entered and the corresponding relationship between the fill-in-blank items and the fields in the target form, the entry results of the multiple fields in the target form are determined.

[0013] The fill-in-the-blank items also include sample information to prompt the information to be entered in the fill-in-the-blank items.

[0014] The guiding copy information may also include keywords, key words and / or punctuation marks;

[0015] The step of identifying the content to be entered corresponding to the fill-in-blank item from the speech recognition result includes:

[0016] According to the keywords, key words and / or punctuation marks included in the guiding copy information, the starting point and the ending point of the content to be entered corresponding to the fill-in-the-blank item are identified from the speech recognition result.

[0017] Among them, it also includes:

[0018] After identifying the content to be entered corresponding to the fill-in-the-blank item from the speech recognition result, an operation option for editing the content to be entered is provided.

[0019] The target form includes: a visit record form required to be entered after visiting the target organization;

[0020] The fill-in-the-blank items include: fill-in-the-blank items for entering information about target visit objects;

[0021] The method further comprises:

[0022] After identifying the information of the target visiting object from the speech recognition result, determining whether the identified target visiting object has an association relationship with the target organization;

[0023] The step of identifying the content to be entered corresponding to the fill-in-blank item from the speech recognition result includes:

[0024] If the identified target visiting object has an association relationship with the target organization, the information of the identified target visiting object is determined as the content to be entered in the corresponding fill-in-the-blank item.

[0025] Among them, it also includes:

[0026] If the identified target visit object has an association relationship with the target organization, the content to be entered is displayed in the corresponding fill-in-the-blank item, and an operation option for editing the content to be entered is provided;

[0027] After receiving the edit request through the operation option, information of other persons associated with the target organization is provided as candidate items according to the pre-stored information of the target organization.

[0028] Among them, it also includes:

[0029] If there is no association relationship between the identified target visiting object and the target organization in the pre-saved information of the target organization, prompt information is provided; the prompt information is used to prompt the user to submit the identified target visiting object for review.

[0030] Among them, it also includes:

[0031] The received voice input information is saved as an audio file, and an operation option for playing back the saved audio file is provided.

[0032] An information entry method, comprising:

[0033] Receiving form input information submitted by a client, the client being used to provide a form input interface, the form input interface including voice input guiding information; the voice input guiding information including a plurality of fill-in-the-blank items and guiding copy information; the guiding copy information being used to string the fill-in-the-blank items into a natural language paragraph, so as to perform voice input based on the natural language paragraph;

[0034] According to the corresponding relationship between the fill-in-the-blank items in the form entry information and the content to be entered, and the corresponding relationship between the fill-in-the-blank items and the fields in the target form, the entry results of the multiple fields in the target form are determined.

[0035] An information input device, comprising:

[0036] A guidance information providing unit, used for providing voice input guidance information in the form input interface; the voice input guidance information includes a plurality of fill-in-the-blank items and guidance copy information; the guidance copy information is used for connecting the fill-in-the-blank items into a natural language paragraph, so as to perform voice input based on the natural language paragraph;

[0037] A speech recognition unit, used for performing speech recognition on received speech input information;

[0038] A to-be-entered content determination unit, used to identify the to-be-entered content corresponding to the fill-in-the-blank item from the speech recognition result;

[0039] The form entry result determination unit is used to determine the entry results of multiple fields in the target form according to the content to be entered and the corresponding relationship between the fill-in items and the fields in the target form.

[0040] An information input device, comprising:

[0041] An information receiving unit, configured to receive form input information submitted by a client, wherein the client is configured to provide a form input interface, wherein the form input interface includes voice input guiding information; the voice input guiding information includes a plurality of fill-in-the-blank items and guiding copy information; the guiding copy information is configured to string the fill-in-the-blank items into a natural language paragraph, so as to perform voice input based on the natural language paragraph;

[0042] The form entry result determination unit is used to determine the entry results of multiple fields in the target form according to the correspondence between the fill-in-blank items in the form entry information and the content to be entered, and the correspondence between the fill-in-blank items and the fields in the target form.

[0043] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any of the methods described above.

[0044] An electronic device, comprising:

[0045] one or more processors; and

[0046] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of any of the methods described above.

[0047] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0048] Through the embodiments of the present application, a form information entry method of voice input can be provided. At the same time, the entry interface of the form is re-layouted. Instead of adopting a layout method of arranging each field from top to bottom, multiple fill-in-the-blank items are connected in series into a natural language paragraph by guiding the copy information, and the specific fill-in-the-blank items can correspond to the specific fields in the form. In this way, when the user enters the form information by voice input, the voice input can be performed by reading the natural language paragraph aloud. The subsequent system can perform voice recognition on the voice input information, and identify the content to be entered corresponding to the fill-in-the-blank item from the voice recognition result, and then determine the entry results of multiple fields in the target form according to the content to be entered and the correspondence between the fill-in-the-blank item and the field. In other words, the user can complete the entry of information on multiple fields through a single voice input, thereby improving the entry efficiency and making the entire solution more in line with the convenience requirements of mobile office in mobile scenarios.

[0049] Of course, any product implementing the present application does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 It is a schematic diagram of the information input interface in the prior art;

[0052] Figure 2 is a schematic diagram of a first information input interface provided in an embodiment of the present application;

[0053] Figure 3 It is a schematic diagram of the system architecture provided by the embodiment of the present application;

[0054] Figure 4 is a flow chart of the first method provided in an embodiment of the present application;

[0055] Figure 5 is a schematic diagram of a customer details information page provided in an embodiment of the present application;

[0056] Figure 6 is a schematic diagram of a second information input interface provided in an embodiment of the present application;

[0057] Figure 7 is a schematic diagram of a third information input interface provided in an embodiment of the present application;

[0058] Figure 8 is a flow chart of the second method provided in an embodiment of the present application;

[0059] Fig. 9 is a schematic diagram of a first device provided in an embodiment of the present application;

[0060] Fig.10 is a schematic diagram of a second device provided in an embodiment of the present application;

[0061] Fig.11 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0063] The embodiments of the present application provide a corresponding solution to the information entry problem involved in mobile applications. In this solution, a form information entry interface can be provided to the user, and a voice input operation option can be provided, so that the user can enter the content in a specific field by voice input. However, if only voice input is provided as an input method, the input efficiency may still be low, and the user may be required to perform multiple manual operations. For example, a form usually includes multiple fields. According to the traditional form entry interface display method, multiple fields are usually displayed from top to bottom. Specifically in the example of entering a visit record form, the display method of the form entry display interface can be as follows: Figure 1 As shown, the fields may include company name, visiting method, company address, main visitor, visiting time, etc. At this time, even if the user can use the voice input input method, it is necessary to perform manual operations to switch the operation focus between different fields multiple times. For example, the user needs to first click on one of the fields to move the operation focus to the input box of the field, and then long press the operation option in the interface to complete the voice input, and modify the recognized text to confirm that it is correct, and then click the next field to move the operation focus to the input box of the next field before entering the next field. After completing the operation focus movement, it is necessary to long press the operation option in the interface again to start the specific voice input, and so on. It can be seen that if the traditional form entry interface display method is still used, it only saves the user's manual operation in the character input process, but it is still necessary to perform multiple manual operations to realize the movement of the operation focus between different fields, and restart the voice input process after each completion of the operation focus movement.

[0064] Based on the above situation, in order to improve the efficiency of voice input in the embodiment of the present application and better meet the needs of mobile or wireless scenarios, in the specific form entry interface, the specific fields to be filled in are no longer arranged in order from top to bottom, but voice entry method guidance information can be provided. Specifically, this guidance information can first include multiple fill-in-the-blank items to correspond to the fields in the form. In addition, corresponding guidance copy information can be provided for the fill-in-the-blank items. Moreover, each fill-in-the-blank item can be connected in series into a natural language paragraph through this guidance copy information.

[0065] Taking the form for entering visit records as an example, the embodiment of the present application can organize multiple fields in a specific form into a paragraph, for example, Figure 2 As shown in 21, the specific paragraph can be "I visited (fill in the blank item 2) at (fill in the blank item 1), the client's position is (fill in the blank item 3), the visiting method is (fill in the blank item 4), and the main discussion during this visit was (fill in the blank item 5)". Among them, each fill-in-the-blank item can correspond to a specific field in the visit record form, for example, the time, the main visitor's name, the main visitor's position, the visiting method, and the visit description. "I am at", "visited", "the client's position is", "the visiting method is", "the main discussion during this visit" can be the specific guiding copy. Through this specific guiding copy, each fill-in-the-blank item can be organized into a natural language paragraph.

[0066] In this way, when the user enters information into a target form through the form entry interface, the user can perform voice input by reading aloud the specific natural language paragraph. For the guide text, the original text (which can be part of the text or all of the text in the guide text) can be directly read out, and for the fill-in-the-blank items, the content to be entered can be read out. In a preferred embodiment, in order to help users more clearly know what information needs to be filled in each fill-in-the-blank item, prompt information can also be provided in the specific fill-in-the-blank item. For example, Figure 2 As shown, before the user starts voice input, the specific fill-in-the-blank items can display exemplary information in gray fonts or the like. This includes example information about time such as "a certain year, a certain month, and a certain day" in the first fill-in-the-blank item, example information about the name of the main visitor such as the name of the person in the second fill-in-the-blank item, and so on. In this way, multiple fields can be connected in series in the form of fill-in-the-blank items through specific guiding texts. After completing the reading of the natural language paragraph, the corresponding content to be entered for each fill-in-the-blank item can be identified from the received voice input information. Afterwards, the entry results of multiple fields in the target form can be determined according to the correspondence between the fill-in-the-blank items and the specific fields.

[0067] That is to say, through the above method, the user can enter a paragraph of speech, and the information to be entered in multiple fields can be reflected in this paragraph. After that, the system can automatically identify the content to be entered in the specific fill-in-the-blank items from this voice input information, and then determine the entry results of multiple fields in the specific form based on the correspondence between the fill-in-the-blank items and the fields. The user only needs to perform voice entry once to complete the entry of multiple fields, and there is no need to repeatedly perform manual operations such as switching the operation focus and restarting the voice input. Therefore, it can reduce the user's manual operations, which is conducive to improving the entry efficiency and is more in line with the convenience characteristics in wireless scenarios.

[0068] The specific guidance copy can play the role of "talking skills". After viewing the guidance copy, the user can know that when performing voice input, only the specific guidance information needs to be followed for voice input, and there is no need to expand other words. Therefore, the user can get a clear mind and solve the problem of not knowing what to say. In addition, since multiple specific fields are reflected in a paragraph in the form of fill-in-the-blank items, a paragraph can usually express a certain context, and this guidance copy can also be configured in a way that conforms to the user's spoken language habits. Therefore, it is convenient for users to remember specific guidance copy. After using this function many times, users do not even need to look at the screen to say the specific guidance copy and the content to be entered. In this way, voice input in mobile scenarios can be further facilitated. For example, users can complete voice input while driving, and so on.

[0069] From the perspective of system architecture, the embodiments of the present application can provide related functions in some application systems related to mobile office, etc. Among them, the specific application system can provide services to users in the form of client-server, and the client can exist in the form of mobile application or mobile web page. Figure 3 As shown, in a customer relationship management system CRM, a specific client can be provided to users such as sales personnel in an enterprise. When using the client to associate customer relationships, the user can select a customer. When visiting a customer, if a visit record form needs to be entered, the solution provided in the embodiment of the present application can be used to complete the entry of the visit record form. Specifically, the user can perform voice input according to the guide text provided in the form information entry page, and can complete the entry of multiple fields at one time, thereby improving efficiency and meeting the convenience characteristics in wireless scenarios.

[0070] The specific implementation scheme provided in the embodiments of the present application is described in detail below.

[0071] Embodiment 1

[0072] First, this embodiment provides an information entry method from the perspective of the client. Figure 4 , the method may specifically include:

[0073] S401: providing voice input guidance information in the form input interface; the voice input guidance information includes a plurality of fill-in-the-blank items and guidance copy information; the guidance copy information is used to string the fill-in-the-blank items into a natural language paragraph, so as to perform voice input based on the natural language paragraph.

[0074] The form described in the embodiment of the present application can have multiple specific types, and the user can initiate the entry operation of the form in multiple ways. For example, in a specific application scenario, the specific form can be a customer visit record form, and the user can initiate the entry operation of this form through the client of the CRM system. For ease of understanding, some basic concepts in the CRM system are briefly introduced below. Through the CRM customer relationship management system, the customers of the enterprise can be divided into customers in the "high seas" and customers in the "private seas". Customers in the "private seas" are the customer resources of the sales staff themselves, while customers in the "high seas" are customer resources within the company that can be used by all sales staff to "grab orders" and follow up. Sales staff can screen customers through the CRM customer relationship management system, keep interested customers in the "private seas", put customers with no intention or weak intention in the "high seas", and other sales staff can also screen customer resources in the high seas. In addition, the CRM customer relationship management system can obtain some basic information of customers through some channels, for example, through the customer's public industrial and commercial information, obtain the customer's address, relevant personnel information, etc.

[0075] For customer resources in the "private sea", such as Figure 5 As shown in the example in, a detailed information interface of a specific customer resource can be provided in the client, and the specific information about the customer that has been obtained in the system can be displayed in the detailed information interface.

[0076] In addition, sales staff can also edit the content in the details information interface. For example, after obtaining more detailed information about the customer, they can enter it into the system through the details information page, or after learning about the customer's personnel changes, they can also update the information in the system through the details information page. For example, you can add more contacts for the customer through the "Add Contact" option.

[0077] Of course, after initiating a request to add a contact, the review process can also be carried out. After the system determines through some means that the added contact is indeed associated with a specific customer, it is added to the customer's contact list, and so on.

[0078] In addition, the details page can also provide an operation entry for entering the visit record form, such as Figure 5 51 in the "record visit", etc. If the salesperson visits the customer, an entry request can be initiated through the operation entrance, and then the form entry interface can be displayed.

[0079] In addition, in the specific implementation, since the same user may visit multiple customers on the same day, the user can enter the detailed information page of each customer one by one, initiate a request to record the visit respectively, and then perform specific input operations in the corresponding form input interface. Alternatively, an interface for recording visits to multiple customers can also be provided. In this case, continuous input of multiple customers based on the same recording can be supported, and then the voice input content can be distinguished by customer keywords, etc., and the recorded visit content corresponding to each customer can be determined.

[0080] In specific implementation, the specific form entry interface can correspond to the type of the target form to be entered. Usually, the insurance policy entry interface corresponding to the same type of form can be the same or similar. For example, the entry interface corresponding to the visit record form can be the same when entering visit record forms corresponding to different customers. That is, it can include the same fill-in-the-blank items and corresponding guide copy. For example, for a customer visit record form, the specific form entry interface can be as follows: Figure 2 shown.

[0081] The specific fill-in-the-blank items may correspond to the fields that need to be filled in the form. For example, if there are 5 required fields in the form, then in the specific guidance information, 5 fill-in-the-blank items can be set, and by adding specific guidance copy, multiple fill-in-the-blank items can be connected into one paragraph. In addition, the corresponding relationship between each fill-in-the-blank item and the field in the form can also be recorded in the background.

[0082] In a specific implementation, since the subsequent step is to identify the content to be entered corresponding to multiple fill-in-the-blank items from a one-time voice input, and the voice input includes not only the content to be entered in the fill-in-the-blank items, but also the original text of the guide text, in order to facilitate more accurate identification of the content to be entered corresponding to each fill-in-the-blank item, the specific guide text can not only play the role of connecting the fill-in-the-blank items in series, but also help the above-mentioned identification. To this end, in a specific implementation, the guide text information can also include keywords, key words and / or punctuation marks, so that after receiving the specific voice input information and obtaining the voice recognition result, the starting point and end point of the content to be entered corresponding to the specific fill-in-the-blank item can be identified from the specific voice recognition result based on the keywords, key words and / or punctuation marks included in the guide text information.

[0083] For example, in Figure 2 the example shown in Figure 2 , in the guiding copywriting "I am here", the word "here" can be the keyword. That is, when the user says "here" in the voice input information, the subsequent content is usually the specific visit date. In the guiding copywriting "visited", the word "visited" can be the keyword, and the subsequent content is usually the name of the main visitor, and so on. In addition, necessary punctuation marks can also be provided to enable the user to consciously break sentences during voice input, facilitating the acquisition of more accurate recognition results.

[0084] It should be noted that in the specific implementation, since the user performs voice input by reading aloud in accordance with the guiding information, the specific guiding copywriting can also be a copywriting that better conforms to the user's spoken input habits. For example, Figure 2 in the example shown in Figure 2 , the filling item corresponding to the specific "visit description" is guided by the copywriting "What was mainly discussed in this visit". Such a description can be more convenient as a reference for voice input and also facilitate the user to remember the specific guiding copywriting. In addition, according to the historical visit records corresponding to different users, the language expression habits of the users can be analyzed, and then personalized guiding copywriting information can be provided to the users according to the different language expression habits of the users.

[0085] Regarding the voice recording operation option, specifically, it can exist in the form of buttons such as Figure 2 "Press and hold to record" in the example shown in Figure 2 . The user can press and hold the button to start voice input and then release it after completing the voice input, and so on.

[0086] Since the guiding information is provided in the embodiments of the present application, during the voice input process, the user can complete the voice recording by reading aloud according to this guiding information. It should be noted that during the voice input process, for the part of the guiding copywriting, the user can directly read out the original text, or the user can also omit some of the words, but it is best to retain the keywords. For example, for the guiding copywriting "The position of the customer is", during the voice input process, the user can also omit the three words "of the customer" and only say "The position is", followed by the specific position name. In this way, only the three words "The position is" can also be used as the guiding information for the field "Position of the main visitor" to identify the content to be entered in this field from the voice recognition result. Or, for the guiding copywriting "What was mainly discussed in this visit", the user can also omit "What was mainly discussed in this" and only say "discussed", and then continue to say the specific content discussed. Or, the user can also omit "discussed" and only say "What was mainly discussed in this", and then continue to say the specific content discussed. For example, "What was mainly discussed in this visit was to reach a consensus on a certain issue...", and so on.

[0087] In addition, in the case of voice input that is not completely in accordance with the guidance copy information, the fill-in-the-blank items corresponding to the field currently being input can also be displayed differently by highlighting (which can be selected manually or automatically). Furthermore, for fill-in-the-blank items of time type, when the user performs voice input, it is not necessary to limit the input method of date information. For example, you can directly say "today", and then it can be automatically translated into the corresponding year, month and day. Location information such as place can also be automatically identified and filled according to positioning information, etc.

[0088] Furthermore, for the details of the specific negotiation, in addition to being input through voice input, OCR (Optical Character Recognition) and other input methods can also be supported. For example, if the user records the negotiation with the customer by handwriting, the electronic file can be directly generated by scanning or photographing the handwritten paper materials, and the specific characters in it can be recognized by OCR recognition, and the recognition results can be filled in the corresponding fill-in-the-blank items, etc. In addition, the scanned or photographed results can be saved in the form of attachments, etc., for subsequent verification and other processing.

[0089] In summary, although specific guiding text information is provided in the embodiments of the present application, the user still has a certain degree of freedom during the voice input process, which allows the user to more flexibly respond to various practical input needs.

[0090] In order to help users better determine the type of information to be filled in a specific fill-in-the-blank item, sample information may be provided in the fill-in-the-blank item to prompt the information to be entered in the fill-in-the-blank item. For example, in a fill-in-the-blank item for entering visit time information, the date of the sample row may be filled in, etc. This prevents users from mistakenly thinking that location information, etc., needs to be entered into the fill-in-the-blank item.

[0091] S402: Perform voice recognition on the received voice input information.

[0092] After receiving specific voice input information, voice recognition can be performed, and on this basis, the content to be entered in the specific fill-in-the-blank items can be identified. It should be noted here that in the specific implementation, voice recognition can be performed after the user completes the entire voice input, and the content to be entered in each fill-in-the-blank item can be identified respectively. Alternatively, real-time voice recognition can also be performed, that is, voice recognition is performed during the user's voice input process, and as the user's voice inputs, the system synchronously completes the automatic filling of the corresponding fill-in-the-blank items, and so on.

[0093] S403: Identify the content to be entered corresponding to the fill-in-the-blank item from the speech recognition result.

[0094] After obtaining the speech recognition result, the content to be entered corresponding to the specific fill-in item can be recognized from it. In specific implementation, to achieve the above purpose, there can be multiple implementation methods. For example, in one method, as described above, since the specific guiding text is usually corresponding to the fill-in item, keywords, key phrases, and / or punctuation can also be provided in the guiding text. Since the content of the guiding text is usually relatively fixed, the starting point and ending point of the content to be entered corresponding to the fill-in item can be recognized by recognizing keywords, key phrases, pause points, etc. For example, the speech recognition result is "I visited Wen Moumou on * month * day in 2021. The customer's position is the chairman. The visiting method is by phone. This visit mainly talked about...". The first word after the keyword "in" is used as the starting point of the content to be entered for the first fill-in item. The first word after the key phrase "visited" is used as the starting point of the content to be entered for the second fill-in item. Through the punctuation mark "comma", the user can pause after saying the name of the main visitor. Therefore, the last word before this pause point can be used as the ending point of the content to be entered for the second fill-in item, and so on.

[0095] In specific implementation, after recognizing the content to be entered in the specific fill-in item, it can be filled into the corresponding fill-in item. For example, for Figure 2 the form entry interface shown in, after the user completes the voice input, the specific displayed interface can be as Figure 6 shown. The user can view the recognition result given by the system from it. However, in actual applications, the recognition result given by the system may be incorrect. For example, it includes speech recognition errors (that is, there may be some errors in the process of converting speech into text), or errors in recognizing the starting point or ending point of the content to be entered in the specific fill-in item, etc. Therefore, after recognizing the content to be entered corresponding to the specific fill-in item from the speech recognition result, operation options for editing the content to be entered can also be provided. The user can edit the recognition result given by the system through this operation option, including performing modification operations, etc.

[0096] In addition, as mentioned above, in a typical scenario of an embodiment of the present application, the specific target form may be a visit record form that needs to be entered after visiting a target organization (for example, a specific company or other customer). At this time, the specific fill-in-the-blank items may include: fill-in-the-blank items for entering information about the target visit object. Among them, the specific visit object is usually a specific employee in the company, etc. In order to improve the authenticity of the information entered by the user, after the information of the target visit object is identified from the speech recognition result, it is also possible to first determine whether the identified target visit object has an association with the target organization based on the pre-saved information of the target organization. If so, the information of the identified target visit object is determined as the content to be entered for the corresponding fill-in-the-blank item.

[0097] Among them, the information of the target organization saved in advance can be, as mentioned above, the address, contact information, contact information, etc. obtained based on the business information published by the organization. In other words, suppose that after visiting a company, the user inputs the visit information by voice and says that he visited Zhang. At this time, after the system recognizes "Zhang" as the visit object, it can first determine whether Zhang is on the company's employee list. If so, "Zhang" can be displayed in the corresponding fill-in-the-blank item. Otherwise, "Zhang" will not be displayed in the corresponding fill-in-the-blank item, but prompt information can be provided, which can be used to prompt the user to add the identified target visit object to the personnel list of the target organization, and after submitting it for review, enter the target form. That is to say, if the person the user visits has not been recorded in the CRM system, he or she cannot be directly filled in as the visit object in the visit record form. The user needs to go to the customer's details page first, add the person visited as the customer's contact, and after the CRM system background reviews and confirms that this person is indeed an employee of the company, the user can continue to complete the information entry operation about the visit.

[0098] In addition, if the identified target visit object has an association relationship with the target organization, and the information of the identified target visit object is also displayed in the corresponding fill-in-the-blank item, at this time, an operation option for editing the information of the target visit object can also be provided. After receiving the edit request through the operation option, the information of other persons who have an association relationship with the target organization can also be provided as candidates based on the pre-saved information of the target organization. For example, the system's recognition result is as follows Figure 6As shown, if the user needs to modify the name of the visit object, he can click the drop-down box behind "Zhang**". The current company's contact list can be displayed. For example, in addition to Zhang**, it can also include Li*, Wang*, etc. At this time, the user can select other contacts from the list to fill in the current blank item.

[0099] S404: Determine the entry results of multiple fields in the target form according to the content to be entered and the corresponding relationship between the fill-in-blank items and the fields in the target form.

[0100] After determining the content to be entered for the specific fill-in-the-blank item, since the specific fill-in-the-blank item has a corresponding relationship with the fields in the target form, the entry results of multiple fields in the specific target form can be determined based on the corresponding relationship.

[0101] In a specific implementation, the received voice input information can also be saved as an audio file, and an operation option for replaying the saved audio file can be provided. The operation option can be located in the detail information page corresponding to the specific customer, so that the user can replay the audio file at any time as needed.

[0102] It should be noted that the specific form entry results may have different uses in different application scenarios. For example, in the "visit recording" scenario, it can be mainly used to help systems such as CRM to accumulate customer information, and then provide some personalized services to users in the future. For example, through the user's visit recording records, the preferences of a specific salesperson when selecting customers can be statistically analyzed, and similar customers can be recommended to the salesperson in the future, etc. In addition, in some other application scenarios, the specific form entry system can also be associated with the reimbursement system, business trip approval flow system, financial system, administrative system or logistics system, etc., to provide functions such as fast reimbursement and fast approval. For example, the specific form entry results can be pushed to other related systems (or, other related systems can also pull from the form entry system), so that the related systems can perform specific reimbursement, approval and other processing based on the information provided by the insurance policy entry system.

[0103] In summary, through the embodiments of the present application, a voice input form information entry method can be provided. At the same time, the entry interface of the form is re-layouted. Instead of adopting a layout method in which each field is arranged from top to bottom, multiple fill-in-the-blank items are connected in series into a natural language paragraph by guiding the copy information, and the specific fill-in-the-blank items can correspond to the specific fields in the form. In this way, when the user enters the form by voice input, the voice input can be performed by reading the natural language paragraph aloud. The subsequent system can perform voice recognition on the voice input information, and identify the content to be entered corresponding to the fill-in-the-blank item from the voice recognition result, and then determine the entry results of multiple fields in the target form according to the content to be entered and the correspondence between the fill-in-the-blank item and the field. In other words, the user can complete the entry of information on multiple fields through a single voice input, thereby improving the entry efficiency and making the entire solution more in line with the convenience requirements of mobile office in mobile scenarios.

[0104] Embodiment 2

[0105] This second embodiment corresponds to the first embodiment and provides an information entry method from the perspective of the server. Figure 8 , the method may include:

[0106] S801: receiving form input information submitted by a client, wherein the client is used to provide a form input interface, wherein the form input interface includes voice input guiding information; the voice input guiding information includes a plurality of fill-in-the-blank items and guiding copy information; the guiding copy information is used to string the fill-in-the-blank items into a natural language paragraph, so as to perform voice input based on the natural language paragraph;

[0107] S802: Determine the entry results of multiple fields in the target form according to the correspondence between the fill-in-the-blank items in the form entry information and the content to be entered, and the correspondence between the fill-in-the-blank items and the fields in the target form.

[0108] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0109] Corresponding to the first embodiment, the present application embodiment also provides an information entry device, see Fig. 9 , the device may include:

[0110] The guidance information providing unit 901 is used to provide voice input guidance information in the form input interface; the voice input guidance information includes a plurality of fill-in-the-blank items and guidance copy information; the guidance copy information is used to connect the fill-in-the-blank items into a natural language paragraph, so as to perform voice input based on the natural language paragraph;

[0111] The speech recognition unit 902 is used to perform speech recognition on the received speech input information;

[0112] A to-be-entered content determination unit 903, configured to identify the to-be-entered content corresponding to the fill-in-blank item from the speech recognition result;

[0113] The form entry result determination unit 904 is used to determine the entry results of multiple fields in the target form according to the content to be entered and the corresponding relationship between the fill-in items and the fields in the target form.

[0114] In a specific implementation, the fill-in-the-blank item may further include sample information to prompt the information to be entered in the fill-in-the-blank item.

[0115] In addition, the guiding copy information may also include keywords, key words and / or punctuation marks;

[0116] The to-be-entered content determination unit may be specifically used for:

[0117] According to the keywords, key words and / or punctuation marks included in the guiding copy information, the starting point and the ending point of the content to be entered corresponding to the fill-in-the-blank item are identified from the speech recognition result.

[0118] In addition, the device may also include:

[0119] The editing option providing unit is used to provide operation options for editing the content to be entered after identifying the content to be entered corresponding to the fill-in-the-blank item from the speech recognition result.

[0120] In specific implementation, the target form includes: a visit record form required to be entered after visiting the target organization;

[0121] The fill-in-the-blank items include: fill-in-the-blank items for entering information about target visit objects;

[0122] At this time, the device may further include:

[0123] A judgment unit, configured to judge whether the identified target visiting object has an association relationship with the target organization after identifying the information of the target visiting object from the speech recognition result;

[0124] At this time, the unit for determining the content to be entered can be specifically used for: if the identified target visiting object has an association relationship with the target organization, then determining the information of the identified target visiting object as the content to be entered for the corresponding fill-in-the-blank item.

[0125] In addition, the device may also include:

[0126] A display unit, for displaying the content to be entered in a corresponding fill-in-the-blank item if the identified target visit object has an association relationship with the target organization, and providing an operation option for editing the content to be entered;

[0127] The candidate item providing unit is used to provide information of other persons associated with the target organization as candidate items according to the pre-stored information of the target organization after receiving the editing request through the operation option.

[0128] Furthermore, it may also include:

[0129] A prompt unit is used to provide prompt information if there is no association relationship between the identified target visiting object and the target organization in the pre-saved information of the target organization; the prompt information is used to prompt the user to submit the identified target visiting object for review.

[0130] In addition, the device may also include:

[0131] The audio file saving unit is used to save the received voice input information as an audio file and provide an operation option for playing back the saved audio file.

[0132] Corresponding to the second embodiment, the present application embodiment also provides an information entry device, see Fig.10 , the device may include:

[0133] The information receiving unit 1001 is used to receive form input information submitted by a client, wherein the client is used to provide a form input interface, wherein the form input interface includes voice input guiding information; the voice input guiding information includes a plurality of fill-in-the-blank items and guiding copy information; the guiding copy information is used to string the fill-in-the-blank items into a natural language paragraph, so as to perform voice input based on the natural language paragraph;

[0134] The form entry result determination unit 1002 is used to determine the entry results of multiple fields in the target form according to the correspondence between the fill-in-the-blank items in the form entry information and the content to be entered, and the correspondence between the fill-in-the-blank items and the fields in the target form.

[0135] In addition, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods in the aforementioned method embodiments are implemented.

[0136] And an electronic device, comprising:

[0137] one or more processors; and

[0138] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in any one of the aforementioned method embodiments.

[0139] in, Fig.11 The architecture of an electronic device is exemplarily shown. For example, device 1100 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, an aircraft, etc.

[0140] Reference Fig.11 , device 1100 may include one or more of the following components: a processing component 1102 , a memory 1104 , a power component 1106 , a multimedia component 1108 , an audio component 1110 , an input / output (I / O) interface 1112 , a sensor component 1114 , and a communication component 1116 .

[0141] The processing component 1102 generally controls the overall operation of the device 1100, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1102 may include one or more processors 1120 to execute instructions to complete all or part of the steps of the method provided by the technical solution of the present disclosure. In addition, the processing component 1102 may include one or more modules to facilitate the interaction between the processing component 1102 and other components. For example, the processing component 1102 may include a multimedia module to facilitate the interaction between the multimedia component 1108 and the processing component 1102.

[0142] The memory 1104 is configured to store various types of data to support operations on the device 1100. Examples of such data include instructions for any application or method operating on the device 1100, contact data, phone book data, messages, pictures, videos, etc. The memory 1104 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0143] The power supply component 1106 provides power to the various components of the device 1100. The power supply component 1106 can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 1100.

[0144] The multimedia component 1108 includes a screen that provides an output interface between the device 1100 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1108 includes a front camera and / or a rear camera. When the device 1100 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0145] The audio component 1110 is configured to output and / or input audio signals. For example, the audio component 1110 includes a microphone (MIC), and when the device 1100 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 1104 or sent via the communication component 1116. In some embodiments, the audio component 1110 also includes a speaker for outputting audio signals.

[0146] I / O interface 1112 provides an interface between processing component 1102 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0147] The sensor assembly 1114 includes one or more sensors for providing various aspects of status assessment for the device 1100. For example, the sensor assembly 1114 can detect the open / closed state of the device 1100, the relative positioning of components, such as the display and keypad of the device 1100, and the sensor assembly 1114 can also detect the position change of the device 1100 or a component of the device 1100, the presence or absence of user contact with the device 1100, the orientation or acceleration / deceleration of the device 1100, and the temperature change of the device 1100. The sensor assembly 1114 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 1114 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1114 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0148] The communication component 1116 is configured to facilitate wired or wireless communication between the device 1100 and other devices. The device 1100 can access a wireless network based on a communication standard, such as WiFi, or a mobile communication network such as 2G, 3G, 4G / LTE, 5G, etc. In an exemplary embodiment, the communication component 1116 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1116 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0149] In an exemplary embodiment, device 1100 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0150] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1104 including instructions, and the above instructions can be executed by a processor 1120 of the device 1100 to complete the method provided by the technical solution of the present disclosure. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0151] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0152] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0153] The above is a detailed introduction to the information entry method, device and electronic device provided by the present application. The principles and implementation methods of the present application are described in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A method for inputting information, characterized in that: include: Display voice input guidance information in the form input interface; The form entry interface includes an interface for entering customer visit record information in a customer relationship management system, the voice entry guide information includes a plurality of fill-in-the-blank items and guide text information; the guide text information is used to string the plurality of fill-in-the-blank items into a natural language paragraph, so as to guide the user to perform voice input based on the natural language paragraph by speaking the contents to be entered in the plurality of fill-in-the-blank items during the process of reading the guide text information aloud; the guide text is a text that conforms to the user's oral input habits, and the natural language paragraph is used to express the context related to entering the customer visit record; Performing speech recognition on the received speech input information; Identifying the content to be entered corresponding to the fill-in items from the speech recognition results; wherein, according to the keywords, key words and / or punctuation included in the guide copy information, identifying the starting points and ending points of the content to be entered corresponding to the multiple fill-in items from the specific speech recognition results; According to the content to be entered and the corresponding relationship between the fill-in-blank items and the fields in the target form, the entry results of the multiple fields in the target form are determined.

2. The method according to claim 1, characterized in that The fill-in-the-blank item also includes sample information to prompt the information to be entered in the fill-in-the-blank item.

3. The method according to claim 1, characterized in that Also includes: After identifying the content to be entered corresponding to the fill-in-the-blank item from the speech recognition result, an operation option for editing the content to be entered is provided.

4. The method according to claim 1, characterized in that The target form includes: a visit record form required to be entered after visiting the target organization; The fill-in-the-blank items include: fill-in-the-blank items for entering information about target visit objects; The method further comprises: After identifying the information of the target visiting object from the speech recognition result, determining whether the identified target visiting object has an association relationship with the target organization; The step of identifying the content to be entered corresponding to the fill-in-blank item from the speech recognition result includes: If the identified target visiting object has an association relationship with the target organization, the information of the identified target visiting object is determined as the content to be entered in the corresponding fill-in-the-blank item.

5. The method according to claim 4, characterized in that Also includes: If the identified target visit object has an association relationship with the target organization, the content to be entered is displayed in the corresponding fill-in-the-blank item, and an operation option for editing the content to be entered is provided; After receiving the edit request through the operation option, information of other persons associated with the target organization is provided as candidate items according to the pre-stored information of the target organization.

6. The method according to claim 5, characterized in that Also includes: If there is no association relationship between the identified target visiting object and the target organization in the pre-saved information of the target organization, prompt information is provided; the prompt information is used to prompt the user to submit the identified target visiting object for review.

7. A method for inputting information, characterized in that: include: Receiving form entry information submitted by a client, the client being used to display a form entry interface, the form entry interface including an interface for entering customer visit record information in a customer relationship management system, the form entry interface including voice entry guidance information; The voice input guidance information includes a plurality of fill-in-the-blank items and guidance text information; the guidance text information is used to connect the plurality of fill-in-the-blank items into a natural language paragraph, so as to guide the user to perform voice input based on the natural language paragraph by speaking the contents to be input in the plurality of fill-in-the-blank items during the process of reading the guidance text information aloud; the guidance text is a text that conforms to the user's oral input habits, and the natural language paragraph is used to express the context related to inputting customer visit records; According to the correspondence between the fill-in-the-blank items in the form entry information and the content to be entered, and the correspondence between the multiple fill-in-the-blank items and the fields in the target form, the entry results of the multiple fields in the target form are determined; wherein, according to the keywords, key words and / or punctuation included in the guide copy information, the starting point and the ending point of the content to be entered corresponding to the specific fill-in-the-blank item are identified from the specific speech recognition results.

8. An information input device, characterized in that: include: A guidance information providing unit, used to display voice input guidance information in the form input interface; The form entry interface includes an interface for entering customer visit record information in a customer relationship management system, the voice entry guide information includes a plurality of fill-in-the-blank items and guide text information; the guide text information is used to string the plurality of fill-in-the-blank items into a natural language paragraph, so as to guide the user to perform voice input based on the natural language paragraph by speaking the contents to be entered in the plurality of fill-in-the-blank items during the process of reading the guide text information aloud; the guide text is a text that conforms to the user's oral input habits, and the natural language paragraph is used to express the context related to entering the customer visit record; A speech recognition unit, used for performing speech recognition on received speech input information; a unit for determining content to be entered, configured to identify the content to be entered corresponding to the fill-in items from the speech recognition results; wherein, according to the keywords, key words and / or punctuation included in the guide copy information, the starting point and the ending point of the content to be entered corresponding to the plurality of fill-in items are identified from the specific speech recognition results; The form entry result determination unit is used to determine the entry results of multiple fields in the target form according to the content to be entered and the corresponding relationship between the fill-in items and the fields in the target form.

9. An information input device, characterized in that: include: An information receiving unit, used to receive form entry information submitted by a client, the client is used to display a form entry interface, the form entry interface includes an interface for entering customer visit record information in a customer relationship management system, and the form entry interface includes voice entry guidance information; The voice input guidance information includes a plurality of fill-in-the-blank items and guidance text information; the guidance text information is used to connect the plurality of fill-in-the-blank items into a natural language paragraph, so as to guide the user to perform voice input based on the natural language paragraph by speaking the contents to be input in the plurality of fill-in-the-blank items during the process of reading the guidance text information aloud; the guidance text is a text that conforms to the user's oral input habits, and the natural language paragraph is used to express the context related to inputting customer visit records; A form entry result determination unit is used to determine the entry results of multiple fields in the target form based on the correspondence between the fill-in-the-blank items in the form entry information and the content to be entered, and the correspondence between the multiple fill-in-the-blank items and the fields in the target form respectively; wherein, based on the keywords, key words and / or punctuation included in the guide copy information, the starting point and the ending point of the content to be entered corresponding to the specific fill-in-the-blank item are identified from the specific speech recognition results.

Images