Method for retrieving business conversation data
By automatically accumulating and managing business conversation data at the end of a business conversation, the information processing device achieves efficient data storage and accurate retrieval, solving the problem of insufficient business conversation data retrieval function in existing technologies and improving data utilization efficiency and predictive capabilities.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-27
- Publication Date
- 2026-04-21
AI Technical Summary
There is room for improvement in existing machine learning capabilities for retrieving business conversation data, particularly in terms of data accuracy and efficiency.
The information processing device automatically accumulates business conversation data at the end of the conversation and achieves efficient storage and accurate retrieval of the data through database management and retrieval condition settings, including the accumulation of text data and the analysis and display of audio data.
It improves the accuracy of data accumulation and retrieval efficiency in business conversations, enabling efficient extraction and display of relevant data from the database based on search criteria. This supports data analysis and prediction of business conversations, enhancing the predictability of business conversations and the efficiency of data utilization.
Smart Images

Figure CN121901360A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to methods for retrieving business conversation data. Background Technology
[0002] A dialogue analysis system is disclosed, which records dialogue data based on audio data obtained from recording dialogue content, extracts dialogues that match conditions specified by the user from the dialogue data, and displays them at a glance. Summary of the Invention
[0003] However, there is room for improvement in the ability to retrieve business conversation data based on past machine learning.
[0004] The purpose of this disclosure is to improve the ability to retrieve data from past business conversations.
[0005] One embodiment of this disclosure is a method performed by an information processing apparatus, comprising:
[0006] Each time a business conversation ends, the business conversation data, including text data related to the content of the business conversation, is accumulated in the database;
[0007] Obtain search criteria;
[0008] Extract business conversation data from the database that meets the obtained search criteria; and
[0009] The extracted business conversation data is displayed on the display unit.
[0010] According to one implementation, the ability to retrieve past business conversation data can be improved. Attached Figure Description
[0011] The features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which the same reference numerals denote the same elements, and are attached as follows:
[0012] Figure 1 This is a block diagram illustrating a structural example of an information processing apparatus according to one embodiment; and
[0013] Figure 2 It is shown Figure 1 A flowchart illustrating the operation of an information processing device. Detailed Implementation
[0014] Hereinafter, with reference to the accompanying drawings, one embodiment of the present disclosure will be described.
[0015] Summary of Implementation Methods
[0016] Figure 1This diagram illustrates a structural example of an information processing apparatus 10 according to one embodiment. The information processing apparatus 10, for example, analyzes recordings of conversations related to the sale of various goods / services, including automobiles and related merchandise and services. Hereinafter, the person receiving the goods / services will sometimes be referred to as a "customer," and any person at the sales outlet providing the goods / services will be referred to as a "salesperson." The following description will focus on an example of using the information processing apparatus 10 for automobile sales, but the application of the information processing apparatus 10 is arbitrary.
[0017] Information processing device 10 is a computer that manages and stores past business conversation data in a database. Information processing device 10 can be, for example, a PC (Personal Computer) or tablet terminal operated by a salesperson, but the type of information processing device 10 is arbitrary. For example, information processing device 10 can also be a computer located in a data center. Information processing device 10 can also be a server belonging to a cloud computing system or other computing system. Information processing device 10 does not need to be implemented through a single device; for example, it can be implemented through communication between a PC or tablet terminal and cloud servers and network storage devices.
[0018] Sales personnel use the information processing device 10 in business conversations with customers. The information processing device 10 acquires and manages audio data from recorded business conversations with the customer's consent, as well as information manually entered by the sales personnel. This business conversation data may include, for example, information related to customer attributes (e.g., gender, age, occupation, family structure, hobbies / activities, etc.) and personal information (e.g., family information, purpose of use, hobbies, life events, living environment, etc.). The information processing device 10 promotes the utilization of sales data by collecting, analyzing, and providing prompts for such information.
[0019] First, an overview of this embodiment will be given; details will follow. Whenever a business conversation ends, the information processing device 10 accumulates business conversation data, including text data related to the content of the business conversation, into a database. The information processing device 10 obtains search criteria. The information processing device 10 extracts business conversation data that matches the obtained search criteria from the database. The information processing device 10 displays the extracted business conversation data on a display unit.
[0020] Thus, according to the information processing device 10, whenever a business conversation ends, the business conversation data is automatically accumulated in the database. After obtaining the search criteria, business conversation data that matches the search criteria is extracted from the database and displayed. Therefore, according to the information processing device 10, for example, compared to the example where all business conversation data is accumulated in the database through manual input, the accuracy of the accumulated business conversation data is improved.
[0021] Structure of Information Processing Device 10
[0022] Figure 1 This is a block diagram showing an example of the structure of an information processing device 10. The information processing device 10 includes a control unit 11, a storage unit 12, a communication unit 13, an input unit 14, and an output unit 15.
[0023] The control unit 11 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor specifically designed for particular processing. The dedicated circuit is, for example, a FPGA (Field-Programmable Gate Array) or an ASIC (Application-Specific Integrated Circuit). The control unit 11 controls the various parts of the information processing device 10 while performing processing related to the operation of the information processing device 10.
[0024] The storage unit 12 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of them. The semiconductor memory is, for example, RAM (Random Access Memory) or ROM (Read Only Memory). RAM is, for example, SRAM (Static Random Access Memory) or DRAM (Dynamic Random Access Memory). ROM is, for example, EEPROM (Electrically Erasable Programmable Read Only Memory). The storage unit 12 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 12 stores data used in the operation of the information processing device 10 and data obtained through the operation of the information processing device 10.
[0025] The communication unit 13 includes at least one external communication interface. This communication interface can be either a wired or wireless communication interface. In the case of wired communication, the communication interface may be, for example, a LAN interface or a USB (Universal Serial Bus). In the case of wireless communication, the communication interface may be, for example, an interface corresponding to mobile communication standards such as LTE (Long Term Evolution), 4G (4th generation), or 5G (5th generation), or an interface corresponding to short-range wireless communication such as Bluetooth (a registered trademark). The communication unit 13 receives data used in the operation of the information processing device 10 and transmits data obtained through the operation of the information processing device 10.
[0026] The input unit 14 includes at least one input interface. The input interface may also include a sound sensor (microphone) for receiving sound input. Alternatively, the input unit 14 may be, for example, a physical button, a capacitive button, a pointing device, or a touchscreen integrated with the display. Furthermore, the input interface may also be, for example, a camera that receives gesture input. The input unit 14 accepts the input of data used in the operation of the information processing device 10. The input unit 14 may also be connected to the information processing device 10 as an external input device, instead of being installed on the information processing device 10. As a connection method, for example, any method such as USB (Universal Serial Bus), HDMI (High-Definition Multimedia Interface), or Bluetooth (Bluetooth) can be used.
[0027] The output unit 15 includes at least one output interface. The output interface may be, for example, a display that outputs image information or a speaker that outputs sound information. The display may be, for example, an LCD (Liquid Crystal Display) or an organic EL (electroluminescence) display. The output unit 15 may also display and output data obtained through the operation of the information processing device 10. The output unit 15 may also be connected to the information processing device 10 as an external output device, instead of being installed on the information processing device 10. As a connection method, for example, any method such as USB, HDMI (registered trademark), or Bluetooth (registered trademark) can be used.
[0028] The functions of the information processing device 10 are implemented by a processor, equivalent to the control unit 11, executing the program described in this embodiment. That is, the functions of the information processing device 10 are implemented through software. The program causes the computer to perform the actions of the information processing device 10, thereby enabling the computer to function as the information processing device 10. In other words, the computer functions as the information processing device 10 by executing the actions of the information processing device 10 according to the program.
[0029] In this embodiment, the program can be pre-recorded on a computer-readable recording medium. Computer-readable recording media include non-transitory computer-readable media, such as magnetic recording devices, optical discs, optical-magnetic recording media, or semiconductor memory. Program distribution can be achieved, for example, by selling, transferring, or renting removable recording media such as DVDs (Digital Versatile Discs) or CD-ROMs (Compact Disc Read Only Memory) containing the program. Alternatively, program distribution can also be achieved by storing the program on the storage device of an external server and sending the program from the external server to other computers. Furthermore, the program can also be provided as a program product.
[0030] Some or all of the functions of the information processing device 10 can also be implemented by a dedicated circuit equivalent to the control unit 11. That is, some or all of the functions of the information processing device 10 can also be implemented by hardware.
[0031] Action Examples
[0032] Figure 2 It is shown Figure 1 A flowchart illustrating the operation of the information processing device 10. (Refer to...) Figure 2 The operation of the information processing device 10 described can also be equivalent to one method of the information processing device 10. Figure 2 The actions of each step can also be executed under the control of the control unit 11 of the information processing device 10. For example, the following processing can also be performed in the case of business conversation.
[0033] In step S1, the control unit 11 of the information processing device 10 acquires business conversation data.
[0034] Specifically, the control unit 11 acquires audio data from recorded business conversations with the customer's consent, as well as information manually input by sales personnel, as business conversation data. Furthermore, the control unit 11 can also acquire information obtained using any sensors, in addition to this information, as business conversation data. For example, the control unit 11 can acquire photographic images of the customer and sales personnel as business conversation data. The control unit 11 can also acquire information detected from this information, indicating the speaker's tone of voice, volume, and the customer's and sales personnel's gestures and expressions, as business conversation data. The control unit 11 can also acquire this business conversation data as text data.
[0035] In step S2, the control unit 11 stores the business conversation data obtained in step S1 into the database.
[0036] Specifically, the control unit 11 may also store business conversation data in a database constructed in the storage unit 12, or in a database constructed in an external device that can communicate with the communication unit 13. The control unit 11 may also store business conversation data in the database each time a business conversation ends.
[0037] In step S3, the control unit 11 obtains the search conditions.
[0038] Specifically, the control unit 11 can also obtain search criteria input by the salesperson. Alternatively, the control unit 11 can analyze business conversation data from the ongoing business conversation to automatically obtain search criteria. The control unit 11 can also analyze voice data related to the salesperson's voice to obtain search criteria. For example, the control unit 11 can also obtain search criteria such as vehicle type search, responsible person search, date and time search, or free word search. Search criteria can also be obtained, for example, by the user inputting search criteria into the conversational AI.
[0039] In step S4, the control unit 11 extracts business conversation data from the database that meets the search criteria obtained in step S3.
[0040] In step S5, the control unit 11 displays the business conversation data extracted in step S4 on the display unit of the output unit 15. After completing the processing in step S5, the control unit 11 terminates the flowchart processing.
[0041] Thus, according to the method disclosed herein, business conversation data is automatically accumulated in a database whenever a business conversation ends. After obtaining search criteria, business conversation data matching those criteria is extracted from the database and displayed. Therefore, according to the method disclosed herein, for example, the accuracy of the accumulated business conversation data is improved compared to an example where a portion of the business conversation data is accumulated in a database through manual input.
[0042] Furthermore, the information processing device 10 accumulates business conversation data, including text data such as voice data or transcription data, into a database, and retrieves past business conversation data using search criteria such as vehicle type, responsible personnel, and date and time of the business conversation. Additionally, the information processing device 10 can also retrieve business conversations that have been sent using specific keywords through free-word search. Therefore, for example, when a new model is released, by extracting past business conversations from customers who have had business conversations with the same vehicle type, data analysis can be made more efficient, even for application scenarios that were difficult to implement in previous structures.
[0043] Furthermore, the information processing device 10 can also acquire business conversation data of a new business conversation from the start to the end of the conversation. The information processing device 10 can also acquire information representing the characteristics of the new business conversation based on the business conversation data, using this information as search criteria. The information processing device 10 can also extract business conversation data that matches the acquired search criteria from a database. The information processing device 10 can also display the extracted business conversation data on the display unit of the output unit 15.
[0044] In this structure, information representing the characteristics of new business conversations is used as search criteria to extract and display business conversation data that matches the search criteria from the database. Therefore, it is possible to predict the progress of currently ongoing business conversations based on past business conversation data.
[0045] Furthermore, the information processing device 10 can also acquire data on the time-varying changes of indicator values obtained from evaluating the content of the new business conversation based on predetermined criteria, using the business conversation data from the new business conversation. Such indicator values could be parameters representing the likelihood of a business conversation taking place, or the customer's intention to purchase a car, etc. These indicator values can also be calculated using a learned model obtained through parsing past business conversation data. The information processing device 10 can also acquire patterns of time-varying changes in indicator values included in the business conversation data from the new business conversation, using these patterns as search criteria.
[0046] According to this structure, the pattern of time-varying indicator values obtained by evaluating the content of new business conversations based on predetermined benchmarks is used as a search criterion to extract and display business conversation data that meets the search criteria from the database. Therefore, according to the method disclosed herein, it is possible to accurately predict the progress of currently ongoing business conversations based on past business conversation data. That is, by extracting and displaying past business conversation data whose time-varying indicator values match those of currently ongoing business conversations, the predictability of business conversations is improved for sales personnel. Therefore, for example, sales personnel can reduce sales activities targeting a customer if the probability of a business conversation being established or the customer's willingness to purchase a car decreases. Alternatively, sales personnel can also choose measures such as increasing the probability of establishing a business conversation based on past business conversation data.
[0047] In addition, the information processing device 10 can also store business conversation data, including text data summarizing the content of the business conversation, into a database.
[0048] Based on this structure, the business conversation data accumulated in the database includes text data that summarizes the content of the business conversations. Therefore, as business conversation data that meets the search criteria, the portion that includes the summary of the business conversation is displayed, allowing sales personnel to easily identify the business conversation data they want.
[0049] In addition, the information processing device 10 can also acquire search criteria (step S3) and display extracted (past) business conversation data (steps S4 and S5) during a new business conversation. For example, sales personnel can input search criteria into the conversational AI during a business conversation.
[0050] This disclosure is not limited to the embodiments described above. For example, multiple blocks described in the block diagram may be merged, or a single block may be divided. Multiple steps described in the flowchart may be executed in a time sequence instead of as described, and may be executed in parallel or in a different order depending on the processing capacity of the device executing each step or as needed. Furthermore, modifications are possible without departing from the spirit of this disclosure.
[0051] Alternatively, for example, the structure and operation of the information processing device 10 can be distributed among multiple computers that can communicate with each other. Alternatively, for example, some or all of the components of the information processing device 10 can be located on cloud servers, network storage devices, or other devices.
[0052] The following examples illustrate a portion of the embodiments of this disclosure. However, it should be noted that the embodiments of this disclosure are not limited to these.
[0053] [Postscript 1]
[0054] A method performed by an information processing apparatus includes:
[0055] Each time a business conversation ends, the business conversation data, including text data related to the content of the business conversation, is accumulated in the database;
[0056] Obtain search criteria;
[0057] Extract business conversation data from the database that meets the obtained search criteria; and
[0058] The extracted business conversation data is displayed on the display unit.
[0059] [Postscript 2]
[0060] According to the method described in Appendix 1, where,
[0061] During the period from the start to the end of a new business conversation, acquire the business conversation data for that new business conversation.
[0062] Based on the business conversation data of the new business conversation, information representing the characteristics of the new business conversation is obtained and used as the search criteria.
[0063] Extract business conversation data that meets the obtained search criteria from the database.
[0064] The extracted business conversation data is displayed on the display unit.
[0065] [Postscript 3]
[0066] According to the method described in Appendix 2, where,
[0067] As business conversation data for the new business conversation, data on the time-varying changes of indicator values obtained by evaluating the content of the new business conversation according to predetermined benchmarks are acquired.
[0068] The time-varying patterns of the indicator values contained in the new business conversation data are obtained as the search criteria.
[0069] [Postscript 4]
[0070] According to the method described in any of Appendix 1 to 3, wherein,
[0071] The business conversation data, which also includes text data summarizing the content of the business conversation, will be stored in the database.
Claims
1. A method executed by an information processing device, comprising: Each time a business conversation ends, the business conversation data, including text data related to the content of the business conversation, is accumulated in the database; Obtain search criteria; Extract business conversation data that meets the obtained search criteria from the database; as well as The extracted business conversation data is displayed on the display unit.
2. The method according to claim 1, wherein, During the period from the start to the end of a new business conversation, acquire the business conversation data for that new business conversation. Based on the business conversation data of the new business conversation, information representing the characteristics of the new business conversation is obtained and used as the search criteria. Extract business conversation data that meets the obtained search criteria from the database. The extracted business conversation data is displayed on the display unit.
3. The method according to claim 2, wherein, As business conversation data for the new business conversation, data on the time-varying changes of indicator values obtained by evaluating the content of the new business conversation according to predetermined benchmarks are acquired. The time-varying patterns of the indicator values contained in the new business conversation data are obtained as the search criteria.
4. The method according to any one of claims 1 to 3, wherein, The business conversation data, which also includes text data summarizing the content of the business conversation, will be stored in the database.