TWM640744U - Habit-Based Voice Search Device - Google Patents

Abstract

The invention provides a voice search device based on usage habits, which includes a database, a voice module and a search module. The database is configured to store a plurality of objects, each of which includes an object feature; the voice module is configured to establish a first voice object condition based on the frequently used predetermined sentence pattern, wherein the first voice object The condition is related to an object characteristic and according to the search context, using the speech recognition phrase relative to the search context to convert the first speech object condition into a first object condition string; and the search module is configured to compare the second an object condition string and the object feature, find the plurality of objects in which the object feature and the first object condition string match each other within a predetermined condition, and generate a search comprising a specific number of the plurality of objects result.

Description

Habit-Based Voice Search Device

This invention relates to a voice search device based on usage habits, especially a search system for finding out mutually matching voice objects in predetermined conditions according to voice object search condition strings.

There are many factors to consider when purchasing real estate, such as: price, location, ratio, square meter, living function, object type, etc. Common real estate search methods use the above aspects as the conditions for customers to search, for example, the total search price is less than one Tens of millions of objects or search for two-bedroom and one-living objects. However, the object results displayed by the customer after searching with the aforementioned orientation are still very messy and disorderly. It still takes a lot of effort and energy to browse and filter each object one by one. This kind of The usual search methods cannot fully meet the needs of customers in purchasing considerations.

Moreover, many customers currently do not only consider the conditions of the object itself when purchasing real estate, but give priority to whether the object where the object is located meets their preferences or needs. That is to say, to find a good house, you must first The concept of finding good objects has gradually become a trend. However, the existing real estate search methods are still based on the conditions of the object itself, or can only query to know which objects are in a certain administrative area. You must click and enter each object category to Knowing the conditions of the object (such as the age of the house, the total price range, etc.), it takes more time for the customer to find a satisfactory object, and the real estate agent cannot smoothly provide the information of the object it sells to the customer through the system.

In addition, with the development of speech technology, speech recognition The counting is also introduced piece by piece to meet the needs of real estate transactions, but the voice recognition rate has always been one of the very troublesome issues. If the frequently recognized results are always not what the user thinks, after a long time, the user will no longer use voice recognition to search.

In addition, the condition parameters required for real estate search are not as simple as a few strings like ordinary searches, and often require basic conditions such as administrative area and price range, otherwise the search range is too wide, and it is easy to be confused. There is a problem of too many results, and it is easy to cause excessive load on the system.

For this reason, the applicant invented the "voice search device based on usage habits" in view of the deficiencies in the prior art to improve the above deficiencies.

Therefore, there is a need for a voice search device based on usage habits that can overcome the problems of the prior art. In order to achieve the above purpose, the invention provides a voice search device based on usage habits, which includes a database, a voice module and a search module. The database is configured to store a plurality of objects, wherein each object includes at least an object feature; the voice module is configured to establish a first voice object condition based on the frequently used predetermined sentence pattern, wherein the first voice object The condition is related to an object characteristic and according to the search context, using the speech recognition phrase relative to the search context to convert the first speech object condition into a first object condition string; and the search module is configured to compare the second An object condition string and the at least object characteristic, find the plurality of objects in which the at least object characteristic and the first object condition string match each other within a predetermined condition, and generate one of the plurality of objects including a specific number Search results.

In order to reduce the error rate of speech recognition, this authoring system will use the speech recognition phrase relative to the search situation according to the search situation, and the Voice object conditions are converted into object condition strings, and then the search process is performed.

Using voice interactive guidance, the first voice object condition that needs to be known in order to search can be completed sequentially, which can reduce the problem of too wide search range and too many results, and can also reduce the load of the system.

The voice search device based on usage habits provided by this creation can fully meet the needs of customers in real estate purchases, that is, the voice search device based on usage habits of this creation is a search method based on object priority, and the user inputs their After the demand for housing types such as objects, what the system presents is the result of the collection of objects. Users can first select the objects they are satisfied with, and then browse the objects for sale, because the objects often reflect the quality of life and other living conditions of the objects. , so through the object-first search method, real estate brokers can effectively provide information on the objects they sell to customers through the system, thereby increasing the chances of matching between the two parties.

10: Voice search device based on usage habits

101: User side

105: Database

106: Multiple objects

110:Voice module

120: Search Module

130: Output module

106A: Object

106B: Object

A01, A02, A03, A04: Object characteristics

S01, S02: Items available for sale

20: System search page

205: Search Type Options

206: Search type options

210: search criteria

211:Search criteria

215: Search button

220: map block

221: mark

222: mark

230:Search result block

231: Item

232: item

30: Execution process

S301, S302, S303, S304, S305, S306, S307, S308: steps

Figure 1 is a schematic diagram showing the voice search device based on usage habits of this creation;

Figure 2 is a schematic diagram showing the database of this creation;

Figure 3 is a schematic diagram showing the system search page of this creation;

Figure 4 is a schematic diagram showing the system search page of this creation;

Fig. 5 is a diagram showing the system search page of this work; and

This creation will be fully understood by the following description of the embodiments, so that those skilled in the art can complete it, but this creation can also be widely implemented with other embodiments. That is to say, the implementation of this creation can not be limited by the following embodiments, but should be based on this creation The patent scope of the filed application shall prevail.

Please refer to Figure 1, which shows a schematic diagram of the habit-based voice search device of the present invention. In Figure 1, the voice search device 10 based on usage habits includes a database 105, a voice module 110, a search module 120, and an output module 130, wherein the database 105 stores a plurality of objects 106 and user habit records, and A plurality of objects 106 have at least one object feature (detailed in FIG. 2 ), and each user habit record includes a predetermined sentence pattern and the selected usage times of the predetermined sentence pattern. In the voice search device 10 based on usage habits, the voice module 110 uses the voice receiving and playing device (that is, hardware components required for conventional voice recognition such as microphones, speakers, etc.) The establishment of a voice object condition is to receive the first voice object condition about the characteristics of the object sent by the user terminal 101, and convert the first voice object condition into The first object condition string.

The predetermined sentence pattern that is frequently used may be determined according to the selected usage times of the predetermined sentence pattern. More specifically, the selected usage times of the predetermined sentence pattern is the first or the top three, and the speech module 110 will designate or randomly designate one of the top three as the frequently used predetermined sentence pattern. However, the voice module 110 still needs to collect and analyze the user's habits before it can sort out the selected usage times of the predetermined sentence pattern. In this regard, before the selected usage times of the predetermined sentence pattern does not reach the predetermined threshold, the voice module 110 will still require the user to select the predetermined sentence pattern, and record the selected predetermined sentence pattern in the database 105, Then the establishment of the first voice object condition will be carried out, and after the selected number of times of the predetermined sentence pattern reaches the predetermined threshold (for example, 10 times), the predetermined sentence pattern will be selected from the database 105. The selected number of times of use is among the top three, and the speech module 110 randomly specifies one of the top three as the frequently used predetermined sentence pattern.

The selection of the above-mentioned predetermined sentence pattern can be selected by the user through button click, voice selection or other means. The predetermined sentence pattern to be used and the order of each syllable in the sentence pattern can be selected. Of course, several groups can be preset by the system for selection. , or defined by the user. The predetermined sentence pattern contains at least two syllables, such as the administrative area and the number of pings. Of course, it can also be the administrative area and other frequently searched conditions, such as the total price, the age of the house, and so on. When performing the first voice object condition based on the predetermined sentence pattern, if the selected predetermined sentence pattern is the administrative area and the number of pings, the system will only accept such as "Daan District, Taipei City" and "30 pings", and the system will first check the first Whether the syllable meets the definition of an administrative area (it can be Daan District, Taipei City, Daan District, Taipei City, Daan District, Beishi City, Daan City, Beishi City), and checks whether the second syllable meets the definition of the number of pings (the number of pings can be 30 or 30 pings), Only then will the establishment of the first voice object condition continue. When the system first checks whether the first syllable conforms to the definition of an administrative region, it mainly checks whether the name of the administrative region exists, and the second syllable part checks whether it contains numbers.

The aforementioned search scenarios include different scenarios such as renting, buying, and selling, and in different search scenarios, there will be corresponding speech recognition phrases for recognition, and the generated first object condition strings also roughly belong to the Speech recognition phrases to reduce erroneous speech recognition. Going a step further, a learning function can also be incorporated.

For example, in the search context of buying a house and selling a house, the same first voice object condition, such as Shuanglian, is more likely to find objects around the Shuanglian MRT station in the search context of buying a house, so the first object condition The character string is more likely to be Shuanglian MRT Station, and in the context of house sales search, it is more likely to find objects around Shuanglian Street, so the first object condition string is more likely to be Shuanglian Street, not Shuanglian Jie transport station.

After the voice module 110 receives the first object condition string sent by the user terminal 101, it sends the received object condition string to the search Module 120, then the search module 120 compares the object condition word string and the object characteristics in the database 105, finds out the objects that match each other in the predetermined conditions and sends the matched objects to the output module 130, and then the output module 130 sends the search result back to the user terminal 101 . Preferably, the search module 120 finds objects that match each other within predetermined conditions and generates a search result containing a specific number of objects, wherein the specific number can be zero or an integer greater than zero.

Please see Figure 2, which shows a schematic diagram of the database of this creation. In FIG. 2 , the database 105 stores an object 106A such as a certain suitable residence and an object 106B such as a certain mansion. For example, the objects can be military villages, rebuilt houses, national houses, collective residential areas, suitable houses, social houses, or apartments, mansions, residential buildings, suites, through-the-sky houses or other houses within a specific range type. Object 106A has object feature A01, for example, the age of the house is 15 years, object feature A02, for example, the number of households in the community to which the object belongs is 20, object feature A03, for example, the living function is a store, and object feature A04, for example, there is a public swimming pool. There are salable items S01 and salable items S02. Object 106B has object characteristic A01 such as house age of 15 years, object characteristic A02 such as the number of households in the community to which the object belongs to 15, and object characteristic A03 such as living function as market, wherein the salable items of object 106B are zero. For example, the characteristics of the object can be the number of houses, the age of the house, the state of public establishment, the number of households in the community to which the object belongs, living functions, the number of square meters of the house, the orientation of the house, and the number of floors of the house. Preferably, the database 105 can store data of one or more objects. Preferably, an object may have one or more object characteristics. Preferably, the salable items of the item may be zero or an integer greater than zero.

The corresponding relationship between the item 106A and the salable item S01 and the salable item S02 needs to be completed through some means, because there is no public information for these corresponding relationships. Specifically, according to the urban area of the township, the location of the land section or the address of the house number in the building area, the total area of land transfer in square meters, the urban land use zoning, the transaction year and month, and the transaction transaction number, transfer level, total number of floors, building type, main purpose, main building materials, year and month of construction completion, total building transfer area in square meters, current building structure, whether there is a management organization, total price yuan, unit price per square meter You can select all of the data such as ruler or object name, or select several from them, and construct the object characteristics of multiple objects, and then disassemble the transaction data into multiple fields for search and comparison. Then, according to the housing conditions of the salable object S01 and the salable object S02, it means comparing the address, the total number of floors, and the year and month of construction completion in the housing conditions with the object characteristics of multiple objects in the database to obtain Search and obtain at least one specific item information corresponding to the housing conditions of the salable item S01 and the salable item S01 , and complete the establishment of the relationship between the item 106A, the salable item S01 , and the salable item S02 .

Please continue to refer to FIG. 1 and FIG. 2, the search module 120 compares the received object condition string with the object characteristics of a plurality of objects 106 in the database 105, and finds objects that match each other within predetermined conditions, for example , the object condition character string is 15 years old, the search module 120 finds out the object characteristics A01 of the object 106A and the object 106B after comparing the object characteristics in the database 105, and the house age is 15 years, so the object that meets the comparison condition That is, the object 106A and the object 106B, and then the search module 120 sends the object 106A and the object 106B to the output module 130 to generate the search result.

In this creation, the search module 120 will perform a comparison within the predetermined conditions, and the predetermined conditions include (1) the object condition string is a value, the characteristics of the housing group are the same as the object condition string, and the search results display completely matching objects; (2) The object condition string is a value, and the characteristics of the housing group are different from the object condition string, then the difference range is the range of the object condition string plus or minus the predetermined value, and the search results show some matching objects; (3) The object condition string is Text, the character of the residential group is the same as the character string of the object condition, the search result will display the object that completely matches; Partially matched objects with similar object condition strings. For example, if the object condition string is that the number of households in the community to which the object belongs is 20, the search module 120 will compare the object characteristics in the database 105 with the search range of 20 plus or minus 5 to 25, and then find out the housing group The characteristic is that the object 106A with 20 households in the community to which the object belongs and the object 106B with the characteristic of 15 households in the community to which the object belongs. In addition to the object 106B in the market, the object 106A with the characteristics of a residential group and a store will also be found with similar characteristics. Among them, markets, stores, etc. belong to similar conditions and need to be summarized and built in advance.

Please refer to Figure 3, which shows a schematic diagram of the system search page of this creation. In FIG. 3 , the system search page 20 includes search type options 205 - 206 , search conditions 210 - 211 and a search button 215 . After the user selects the type option and enters the search condition and clicks the search button 215, the object condition string will be sent to the voice module of the system of this invention. Preferably, the search type option 205 and the search condition 210 are required input data, and the search type option 206 and the search condition 211 are optional input data. If the user wants to input multiple search data, he can click on the system search page 20 "+" to create a new search type option and search criteria field.

Please refer to Figure 4, which shows a schematic diagram of the system search page of this creation. In Fig. 4, the system search page 20 further includes a map block 220 and a search result block 230, wherein the map block 220 displays the position on the map of the search result objects, for example, the object 106A is represented by a mark 221 and the object 106B This is indicated by a marker 222 , while the search result block 230 displays the names of the objects in the search results, for example, item 106A is indicated by item 231 and object 106B is indicated by item 232 . For example, after the user sends the object condition string, such as the voice module of the system created by the house aged 15 years, after searching the module and comparing the database, the The output module sends back the system search page 20 to the system search page 20 with the object 106A, such as a suitable residence and the object 106B, such as a certain mansion, having the characteristics of the housing group A01, such as a house with a house age of 15 years, wherein the search module finds out the matching object. It will reconfirm whether the matching item has a salable item. If the matching item does not have a salable item, it will be included in the unmatched item and removed from the comparison result, that is, the search result does not show that it meets the comparison condition but Items without any salable item information, in this example, item 106A has a salable item S01 and a salable item S02 and item 106B has a salable item S01, so they are all items that have a salable item and meet the comparison conditions. In addition , the search module will also sort the items in the search results from the most to the least according to the number of available items in the items that meet the comparison conditions. For example, item 106A has more available items than item 106B, so the sorting It is higher than the item 106B, so that the user can know which items meet the search criteria and have salable items, and at the same time, can preferentially select the items with more salable items.

Please refer to Figure 5, which shows a schematic diagram of the system search page of this creation. Figure 5 is a continuation of Figure 4. After the user obtains the preliminary search result, he performs an operation related to the second voice object condition of the object feature, and the voice module 110 uses the corresponding search context according to the search context. The voice recognition phrase converts the second voice object condition into a second object condition string, and then uses the second object condition string to perform a re-search in the preliminary search result, wherein the data of the preliminary search result has been stored in the user end, so the re-search will only read the cache of the user end, and will not re-access the database, so as to reduce the burden on the database.

More specifically, the search module compares the second object condition string with an object feature of the objects that meet the comparison condition in the preliminary search results, and finds out that at least one residential group feature and the second object condition string are in the predetermined condition Objects that match each other in the object, and generate a re-search result containing the object that meets the comparison condition, if the search module compares the second object condition string with In the search results, after one object feature of the objects that meet the comparison conditions is found, at least one residential group feature and the second object condition string match each other within the predetermined condition, and then the search module is removed from the search results Objects that do not match and match objects appear in the re-search results. For example, the user sends the second object condition word string such as a swimming pool, and only the object 106A in the preliminary search results has the characteristics of residential groups A04, such as a public swimming pool, so the system search page 20 according to the second object condition The string removes the object 106B from the map block 220 and the search result block 230, leaving only the matching object 106A, which is the re-search result. Preferably, if the search module does not find an object feature and the second object condition string that match each other within the predetermined conditions after comparing the second object condition string with the object features that meet the comparison conditions in the preliminary search results object, the re-search results are the same as the initial search results.

This creation is disclosed with reference to the above-mentioned preferred embodiments and examples, and readers should understand that these examples are used for description rather than limitation. Anyone who is familiar with this skill can make various combinations and modifications without departing from the spirit and scope of this creation, and it should still fall within the scope of this creation patent.

10: Voice search device based on usage habits

101: User side

105: Database

106: Multiple objects

110:Voice module

120: Search Module

130: Output module

Claims (10)

A voice search device based on usage habits, comprising: a database configured to store a plurality of objects and a plurality of user habit records, wherein each object includes an object feature, and each user habit record includes a predetermined sentence type and a selected number of times of use of the predetermined sentence pattern; a communication module; a voice module configured to use a sound receiving and playback device based on the frequently used predetermined sentence pattern through the communication module establishment of a first speech object condition, wherein the predetermined sentence pattern contains at least two syllables and the first speech object condition is related to an object feature, and then according to a search context, using a speech recognition phrase relative to the search context, Converting the first voice object condition into a first object condition word string, wherein the frequently used predetermined sentence pattern can be determined according to the selected usage times of the predetermined sentence pattern; and a search module configured to compare For the first object condition string and the object feature, find the plurality of objects whose object feature and the first object condition string match each other within a predetermined condition, and generate the plurality of objects including a specific number One of the search results. The voice search device based on usage habits as described in Item 1 of the scope of the patent application, wherein said matching within the predetermined condition means that the first object condition word string falls within a difference range of at least one residential group characteristic. The voice search device based on usage habits as described in item 2 of the scope of the patent application, wherein the mutual matching within the predetermined conditions includes: (1) the first object condition string is a value, and the at least one residential group feature and The first object condition string is the same, and the search result shows completely matching objects; (2) the first object condition string is a value, and the at least one residential group feature is the same as the first If the object condition strings are different, the difference range is the range of the first object condition string plus or minus a predetermined value, and the search results show partially matched objects; (3) the first object condition string is text, and the at least one The characteristics of the residential group are the same as the first object condition string, and the search results show objects that fully match; and (4) the first object condition string is text, and the at least one residential group characteristic is the same as the first object condition string If they are different, the search result displays objects that partially match the at least one residential group feature and the condition string of the first object. The voice search device based on usage habits as described in item 3 of the scope of patent application, wherein the voice module is configured to receive a second voice object condition related to the object feature, and according to the search situation, use the corresponding The voice recognition phrase of the search context converts the second voice object condition into a second object condition string. The voice search device based on usage habits as described in claim 4 of the patent application, wherein the search module is configured to compare the second object condition string with the plurality of objects in the search result that meet the comparison conditions The feature of the object is to find the plurality of objects that match the characteristics of at least one residential group and the second object condition string in the predetermined condition, and generate a re-search result that includes the plurality of objects that meet the comparison condition. , wherein if the search module finds the characteristics of at least one residential group and the second object after comparing the second object condition string with the object characteristics of the plurality of objects that meet the comparison conditions in the search result If the condition strings match each other in the predetermined condition, the search module removes the unmatched objects from the search result and presents the matched objects in the re-search result. The voice search device based on usage habits as described in item 5 of the scope of the patent application, wherein the comparison of the second object condition string is read from the cache data to generate the comparison of the first object condition string without having to re-access the data in the database. The voice search device based on usage habits as described in item 5 of the scope of the patent application, wherein the database is further configured to store a salable item data of each item and the search module is configured to compare and match the matching conditions According to the quantity of the salable item data in the multiple items that meet the comparison conditions, the search results and the re-search results are sorted from the largest to the least. The plural objects of . The voice search device based on usage habits as described in item 5 of the scope of the patent application, wherein if there is no data on a salable item among the plurality of items that meet the comparison conditions, the search result does not match the re-search result The plurality of objects for the comparison condition. The voice search device based on usage habits as described in item 4 of the scope of patent application, wherein the feature of the object is selected from a number of houses, a house age, a public status, a number of community households to which the object belongs, a living function, a A group formed by the number of square meters of a house, the orientation of a house, the number of floors of a house and their combinations. The voice search device based on usage habits as described in item 1 of the scope of the patent application, wherein the voice module will ask the user to select the predetermined sentence pattern before the number of times the predetermined sentence pattern is used does not reach a predetermined threshold , the establishment of the first voice object condition will be carried out. After the selected use times of the predetermined sentence pattern reach the predetermined threshold, the selected use times of the predetermined sentence pattern are among the top three, and the voice model The group will randomly designate one of the first three as this predetermined sentence pattern that is often used.

Images